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. 43378
    Prev
    Next
    INDEX
    Explanations

    words related to electronic music and its industry

    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
    690
    +0.11
    0.5%
    319
    +0.11
    0.5%
    270
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.11
    0.01
    690
    +0.11
    0.01
    326
    +0.10
    0.01
    Negative Logits
    tons
    -0.87
     Rockies
    -0.69
     Parables
    -0.64
    hee
    -0.61
     Newfoundland
    -0.60
    hips
    -0.60
    aways
    -0.60
     Albion
    -0.59
     skirts
    -0.59
     Kubrick
    -0.58
    POSITIVE LOGITS
    ERG
    1.15
    igration
    1.03
    ILY
    1.03
    igrant
    1.01
    igrants
    0.98
    ISSION
    0.95
    PL
    0.94
    phal
    0.93
    otion
    0.92
    otional
    0.90
    Activations Density 0.005%

    No Known Activations