© 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 EvalsExportsAPI 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. 7016
    Prev
    Next
    INDEX
    Explanations

    words related to doors or entrances

    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
    194
    +0.17
    0.5%
    526
    +0.17
    0.5%
    288
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.17
    0.04
    325
    +0.17
    0.04
    234
    +0.17
    0.04
    Negative Logits
    TING
    -1.11
    ual
    -1.09
    ting
    -1.07
    irtual
    -1.06
    ollah
    -1.05
    ovych
    -1.03
    ivia
    -0.99
    yss
    -0.97
    yan
    -0.97
    udeb
    -0.97
    POSITIVE LOGITS
    steps
    1.82
    door
    1.70
    bell
    1.69
    doors
    1.56
    holes
    1.47
    posts
    1.46
     doors
    1.44
    keepers
    1.41
    frame
    1.41
    ways
    1.40
    Activations Density 0.628%

    No Known Activations