© 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. 45956
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships and personal experiences

    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
    +0.18
    0.9%
    180
    +0.09
    0.5%
    446
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    355
    +0.18
    0.08
    649
    +0.09
    0.02
    759
    +0.09
    0.09
    Negative Logits
     themselves
    -0.72
    atum
    -0.62
    idates
    -0.61
    ãĤª
    -0.56
     yourselves
    -0.55
    pire
    -0.52
     Qatar
    -0.52
    ikhail
    -0.51
     himself
    -0.51
     Himself
    -0.50
    POSITIVE LOGITS
     myself
    0.72
    husband
    0.68
     colleague
    0.63
     niece
    0.62
     friends
    0.61
    ventures
    0.61
    friends
    0.59
    poke
    0.59
     colleagues
    0.58
    collection
    0.57
    Activations Density 15.644%

    No Known Activations