© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 2679
    Prev
    Next
    INDEX
    Explanations

    proper nouns and geographic locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    730
    +0.17
    0.6%
    430
    +0.14
    0.5%
    233
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    730
    +0.17
    0.04
    299
    +0.14
    0.04
    659
    +0.13
    0.04
    Negative Logits
     Dys
    -0.88
    glers
    -0.85
     steroids
    -0.80
    abouts
    -0.79
    Topics
    -0.75
     favor
    -0.73
     dys
    -0.72
    rett
    -0.71
     silhou
    -0.70
     Appalach
    -0.70
    POSITIVE LOGITS
    eer
    0.90
    ATA
    0.90
    escal
    0.86
    Gas
    0.85
    士
    0.84
    Oracle
    0.83
    aton
    0.81
     Unified
    0.80
    CI
    0.79
    rc
    0.78
    Activations Density 0.298%

    No Known Activations