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. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 7879
    Prev
    Next
    INDEX
    Explanations

    references to the movie "Batman v Superman."

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    515
    +0.12
    0.6%
    320
    +0.11
    0.5%
    314
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    515
    +0.12
    0.03
    232
    +0.11
    0.03
    187
    +0.11
    0.03
    Negative Logits
    èĥ
    -0.85
    RIPT
    -0.79
    åī
    -0.76
    使
    -0.75
    ="#
    -0.71
    èª
    -0.69
    PsyNetMessage
    -0.69
    ENC
    -0.67
    æĸ
    -0.67
    åĪ
    -0.66
    POSITIVE LOGITS
    uscript
    1.55
    fred
    1.33
    hattan
    1.31
    oeuv
    1.23
    ifest
    1.23
    agers
    1.21
    agements
    1.17
    hunt
    1.15
    iac
    1.08
    WithNo
    1.05
    Activations Density 0.036%

    No Known Activations