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 3072
    5. 8-RES_FS3072-JB
    6. 1528
    Prev
    Next
    INDEX
    Explanations

    information about missing persons or descriptions of individuals

    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
    678
    +0.11
    0.5%
    412
    +0.10
    0.4%
    33
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.11
    0.09
    570
    +0.10
    0.02
    35
    +0.09
    0.07
    Negative Logits
    Hide
    -0.70
    tnc
    -0.65
    à¨
    -0.61
    nu
    -0.58
    ullah
    -0.57
     grievances
    -0.57
    icons
    -0.56
     coordin
    -0.55
     scapego
    -0.55
    tracks
    -0.54
    POSITIVE LOGITS
     apiece
    1.03
     increments
    0.92
     respectively
    0.89
     compared
    0.86
    depending
    0.82
    illion
    0.81
    elsius
    0.80
    ilion
    0.78
     total
    0.78
    ategory
    0.73
    Activations Density 2.169%

    No Known Activations