© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 3072
    9. 8-RES_FS3072-JB
    11. 2971
    Prev
    Next
    INDEX
    Explanations

    personal identifiers and specific details related to individuals or groups

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    679
    +0.14
    0.7%
    743
    +0.11
    0.5%
    129
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.08
    679
    +0.11
    0.08
    1
    +0.11
    0.06
    Negative Logits
    orld
    -0.81
    fare
    -0.79
    orah
    -0.74
    stead
    -0.68
    ovie
    -0.66
    aptic
    -0.64
    uden
    -0.64
    oil
    -0.64
    ffield
    -0.63
    athi
    -0.62
    POSITIVE LOGITS
    ively
    0.79
    ãĤ¿
    0.76
    ifiable
    0.75
    aho
    0.74
    idable
    0.73
    IFIED
    0.72
    entity
    0.72
    gru
    0.70
    iom
    0.70
    ibly
    0.69
    Activations Density 0.955%

    No Known Activations