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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 34098
    Prev
    Next
    INDEX
    Explanations

    specific dates and timestamps

    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
    +0.17
    0.8%
    258
    +0.10
    0.4%
    98
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.17
    0.09
    393
    +0.10
    0.32
    680
    +0.09
    0.09
    Negative Logits
    rium
    -0.69
    ãĤª
    -0.68
    cel
    -0.64
    rahim
    -0.62
    ctors
    -0.61
    igham
    -0.60
    ãĥĥãĥī
    -0.59
    tyard
    -0.58
    paio
    -0.57
    angelo
    -0.56
    POSITIVE LOGITS
    gest
    0.60
     September
    0.60
     Sept
    0.59
    geries
    0.58
    estone
    0.58
    berries
    0.58
    worms
    0.58
     Ago
    0.58
     date
    0.57
    lement
    0.57
    Activations Density 16.637%

    No Known Activations