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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13751
    Prev
    Next
    INDEX
    Explanations

    medical and health-related terms, including institutions, conditions, and legislative acts, as well as information related to children's welfare and rights

    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
    550
    +0.13
    0.5%
    285
    +0.13
    0.5%
    643
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.06
    628
    +0.13
    0.04
    232
    +0.13
    0.04
    Negative Logits
     Shutterstock
    -0.86
    auga
    -0.78
    pez
    -0.76
     afar
    -0.76
    allery
    -0.75
    iage
    -0.75
     gener
    -0.71
    orescence
    -0.71
    ources
    -0.70
     estab
    -0.69
    POSITIVE LOGITS
    birth
    1.03
    Care
    0.97
    care
    0.94
     Care
    0.94
     Abuse
    0.89
    iatric
    0.88
    Guard
    0.87
    iovascular
    0.82
    lov
    0.81
     Cancer
    0.80
    Activations Density 0.340%

    No Known Activations