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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 1231
    Prev
    Next
    INDEX
    Explanations

    words related to quality, value, importance, and impact

    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
    217
    +0.10
    0.5%
    512
    +0.10
    0.4%
    130
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.07
    322
    +0.10
    0.06
    311
    +0.10
    0.01
    Negative Logits
    idav
    -0.76
    plets
    -0.67
    Downloadha
    -0.61
    Shut
    -0.60
    ansas
    -0.60
     Casino
    -0.59
    etsk
    -0.57
    adan
    -0.56
     bulldo
    -0.54
    MAP
    -0.54
    POSITIVE LOGITS
     stature
    1.06
     caliber
    1.03
    course
    1.01
     il
    0.99
     calib
    0.98
     sorts
    0.93
     magnitude
    0.93
     utmost
    0.92
     importance
    0.92
     renown
    0.90
    Activations Density 1.280%

    No Known Activations