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. 1456
    Prev
    Next
    INDEX
    Explanations

    names of countries and political figures

    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
    19
    +0.11
    0.5%
    429
    +0.10
    0.5%
    210
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.11
    0.04
    314
    +0.10
    -0.00
    462
    +0.10
    0.07
    Negative Logits
    ONEY
    -0.68
    GMT
    -0.61
     ende
    -0.60
    irlf
    -0.59
    pak
    -0.58
    SHARE
    -0.57
    pu
    -0.57
    CHECK
    -0.56
    KEY
    -0.56
    natureconservancy
    -0.56
    POSITIVE LOGITS
    tenance
    0.91
    osterone
    0.91
    llor
    0.78
    roying
    0.77
    riors
    0.75
     hybrids
    0.71
    vised
    0.68
    quartered
    0.68
    pared
    0.66
    acters
    0.66
    Activations Density 1.235%

    No Known Activations