© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 36869
    Prev
    Next
    INDEX
    Explanations

    provocative and controversial statements or content, including references to violence or sensitive topics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Layer 6 UMAP region: Local cluster above bottom line touching e2e-recon cluster - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.36
    2.1%
    640
    +0.16
    0.9%
    679
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.36
    0.39
    6
    +0.16
    0.32
    679
    +0.14
    0.34
    Negative Logits
     organis
    -0.68
     emanc
    -0.61
    emaker
    -0.60
     enrol
    -0.60
     informed
    -0.60
     affili
    -0.59
     advis
    -0.59
     facult
    -0.58
     employment
    -0.57
     lear
    -0.57
    POSITIVE LOGITS
     Seriously
    1.07
     Anyway
    1.00
     Maybe
    0.98
     Needless
    0.95
     Thankfully
    0.94
     Oops
    0.91
     Luckily
    0.91
     That
    0.90
     Wouldn
    0.90
     Apparently
    0.90
    Activations Density 13.336%

    No Known Activations