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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 222
    Prev
    Next
    INDEX
    Explanations

    legal language and names of legal firms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    409
    +0.10
    0.5%
    416
    +0.10
    0.5%
    702
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.06
    409
    +0.10
    0.05
    659
    +0.10
    0.05
    Negative Logits
     Bows
    -0.87
     ANG
    -0.87
     bow
    -0.81
    steen
    -0.79
     swast
    -0.79
     Strength
    -0.78
     AX
    -0.77
    çīĪ
    -0.77
    ograph
    -0.76
     Bow
    -0.75
    POSITIVE LOGITS
    ori
    0.93
    itt
    0.92
    ll
    0.89
    ale
    0.88
    ee
    0.85
    alled
    0.84
    ali
    0.84
    lett
    0.84
    arrell
    0.84
    ett
    0.84
    Activations Density 0.360%

    No Known Activations