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 49152
    5. 8-RES_FS49152-JB
    6. 12195
    Prev
    Next
    INDEX
    Explanations

    terms related to diverse themes in films or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    447
    +0.23
    1.1%
    481
    +0.15
    0.7%
    623
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    623
    +0.23
    0.03
    288
    +0.15
    0.04
    609
    +0.10
    0.03
    Negative Logits
    blance
    -0.73
    TEXTURE
    -0.72
    urations
    -0.67
     Canaver
    -0.67
    ISTORY
    -0.67
    Newsletter
    -0.67
     Thrones
    -0.66
    such
    -0.65
    ynthesis
    -0.63
    olutions
    -0.63
    POSITIVE LOGITS
     english
    0.77
     dmg
    0.72
     americ
    0.68
     sage
    0.66
     poster
    0.65
     pts
    0.65
     info
    0.65
     scout
    0.64
     blend
    0.64
     sleeper
    0.64
    Activations Density 0.194%

    No Known Activations