Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 45589
    Prev
    Next
    INDEX
    Explanations

    email related text

    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
    521
    +0.13
    0.6%
    211
    +0.12
    0.6%
    150
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    374
    +0.13
    0.04
    591
    +0.12
    0.04
    598
    +0.09
    0.03
    Negative Logits
    bats
    -0.87
    SPONSORED
    -0.74
     cabinets
    -0.71
    nels
    -0.68
    soDeliveryDate
    -0.66
    Stud
    -0.64
    abouts
    -0.64
    hend
    -0.64
    OPS
    -0.63
    kees
    -0.62
    POSITIVE LOGITS
     occurred
    0.71
     Cancel
    0.70
     allegation
    0.63
     inacc
    0.63
    ]}
    0.63
     Error
    0.62
     omission
    0.59
     error
    0.58
     Invalid
    0.58
     Failed
    0.57
    Activations Density 5.272%

    No Known Activations