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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45542
    Prev
    Next
    INDEX
    Explanations

    references to Zimbabwe and its political situation

    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
    481
    +0.17
    0.8%
    288
    +0.14
    0.7%
    643
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    643
    +0.17
    0.01
    288
    +0.14
    0.01
    384
    +0.12
    0.01
    Negative Logits
    insula
    -0.80
    ++++++++++++++++
    -0.77
    naissance
    -0.76
    ccording
    -0.71
    mble
    -0.66
     Lauder
    -0.64
    creen
    -0.64
    htaking
    -0.64
    audi
    -0.63
    alty
    -0.63
    POSITIVE LOGITS
    esi
    0.82
    an
    0.81
    uru
    0.74
    istani
    0.74
    ans
    0.73
    andan
    0.73
    ano
    0.72
    imbabwe
    0.71
    ANS
    0.71
    verning
    0.69
    Activations Density 0.006%

    No Known Activations