© 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. 8573
    Prev
    Next
    INDEX
    Explanations

    simple physical actions or interactions that involve touch

    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
    288
    +0.13
    0.6%
    540
    +0.11
    0.5%
    162
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.21
    540
    +0.11
    0.19
    78
    +0.10
    0.13
    Negative Logits
     stockp
    -0.75
     exhibits
    -0.74
     arsen
    -0.71
     notor
    -0.69
     destruct
    -0.67
     contracting
    -0.67
    NetMessage
    -0.66
     classrooms
    -0.66
     warehouses
    -0.63
     sights
    -0.63
    POSITIVE LOGITS
    able
    0.84
    ishment
    0.82
    athon
    0.80
    uation
    0.78
    imei
    0.75
    idity
    0.74
    phrase
    0.73
    DOWN
    0.73
    ably
    0.72
    BACK
    0.72
    Activations Density 4.247%

    No Known Activations