© 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 Local
    9. 6-RES_SCL-AJT
    11. 45930
    Prev
    Next
    INDEX
    Explanations

    mentions of treatments for various medical conditions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.16
    0.8%
    507
    +0.11
    0.6%
    420
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.16
    0.18
    362
    +0.11
    0.13
    97
    +0.09
    0.07
    Negative Logits
     Vide
    -0.58
     Aerospace
    -0.57
    arrass
    -0.56
    gow
    -0.55
    inet
    -0.54
    asketball
    -0.53
    inx
    -0.52
    ova
    -0.51
     bidding
    -0.51
    hover
    -0.51
    POSITIVE LOGITS
    ises
    0.93
    ments
    0.83
     illnesses
    0.80
     ailments
    0.76
    ise
    0.76
     diseases
    0.76
    ties
    0.73
     patients
    0.69
     illness
    0.68
    ts
    0.68
    Activations Density 8.637%

    No Known Activations