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. 7617
    Prev
    Next
    INDEX
    Explanations

    statements regarding looking forward to future collaborations or actions

    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
    608
    +0.11
    0.5%
    143
    +0.10
    0.4%
    481
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    90
    +0.11
    0.02
    608
    +0.10
    0.02
    105
    +0.10
    0.02
    Negative Logits
    soDeliveryDate
    -0.77
    owned
    -0.73
    are
    -0.69
    MRI
    -0.67
    Viol
    -0.67
    worth
    -0.67
    esp
    -0.66
    maxwell
    -0.65
    Wallet
    -0.65
    roy
    -0.64
    POSITIVE LOGITS
     seeing
    1.06
     hearing
    1.03
     welcoming
    0.94
     presenting
    0.85
     someday
    0.85
     completing
    0.85
     chatting
    0.83
     receiving
    0.83
     unveiling
    0.82
     answering
    0.82
    Activations Density 0.050%

    No Known Activations