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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 877
    Prev
    Next
    INDEX
    Explanations

    proper names of music venues

    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
    437
    +0.11
    0.5%
    757
    +0.11
    0.5%
    415
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    515
    +0.11
    0.01
    232
    +0.11
    0.01
    757
    +0.11
    0.01
    Negative Logits
    dash
    -0.72
    intosh
    -0.71
    ARR
    -0.71
     hed
    -0.67
     actionGroup
    -0.64
    matically
    -0.59
     tremend
    -0.59
    ãĤ¼ãĤ¦ãĤ¹
    -0.59
     ACTIONS
    -0.58
    ONT
    -0.58
    POSITIVE LOGITS
    ues
    0.99
    uers
    0.92
    cius
    0.89
    ue
    0.84
    acular
    0.82
    uous
    0.82
    apore
    0.82
    eto
    0.82
    ante
    0.81
    ison
    0.81
    Activations Density 0.017%

    No Known Activations