© 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. 36935
    Prev
    Next
    INDEX
    Explanations

    text related to software functionality and features

    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: Mixed in middle - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.10
    0.9%
    288
    +0.07
    0.6%
    724
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.10
    -0.01
    497
    +0.07
    0.13
    724
    +0.06
    0.15
    Negative Logits
    eting
    -0.41
    76561
    -0.40
    ioxide
    -0.39
    amer
    -0.36
    vol
    -0.36
    Rated
    -0.35
     Citizen
    -0.35
     istg
    -0.35
     Poster
    -0.34
    apers
    -0.34
    POSITIVE LOGITS
    ality
    0.45
    witz
    0.44
     quirks
    0.42
     richness
    0.41
     Provided
    0.40
    jriwal
    0.39
     functionality
    0.38
    iencies
    0.37
    HUD
    0.37
     implemented
    0.37
    Activations Density 10.383%

    No Known Activations