© 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. 844
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    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
    459
    +0.11
    0.4%
    299
    +0.11
    0.4%
    476
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    299
    +0.11
    0.03
    232
    +0.11
    0.02
    767
    +0.11
    0.02
    Negative Logits
     rightful
    -0.81
    sonian
    -0.81
    ersen
    -0.73
     dilig
    -0.72
    Versions
    -0.72
     adolesc
    -0.72
    Henry
    -0.70
    umenthal
    -0.69
    named
    -0.68
     appropriation
    -0.67
    POSITIVE LOGITS
    ooth
    1.16
    adesh
    0.93
    aby
    0.82
    inka
    0.81
    ucc
    0.81
    oths
    0.81
    oth
    0.78
    henko
    0.77
    azing
    0.77
    obo
    0.77
    Activations Density 0.097%

    No Known Activations