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. 1548
    Prev
    Next
    INDEX
    Explanations

    verbs related to forceful actions or outcomes

    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
    431
    +0.12
    0.5%
    702
    +0.10
    0.5%
    151
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.07
    203
    +0.10
    0.04
    151
    +0.10
    0.05
    Negative Logits
    ikarp
    -0.81
    umption
    -0.76
    maxwell
    -0.76
    anooga
    -0.75
    itive
    -0.73
    HUD
    -0.71
    atts
    -0.70
    glomer
    -0.69
    ŀ
    -0.68
    IVERS
    -0.68
    POSITIVE LOGITS
     striking
    0.78
     strike
    0.78
    breakers
    0.74
    ters
    0.68
     struck
    0.67
     resemblance
    0.66
     resemb
    0.65
    out
    0.64
     strikes
    0.64
     similarities
    0.63
    Activations Density 0.810%

    No Known Activations