© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 18872
    Prev
    Next
    INDEX
    Explanations

    mentions of "Computer Science" and related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    167
    +0.14
    0.6%
    288
    +0.14
    0.6%
    706
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    137
    +0.14
    0.02
    706
    +0.14
    0.03
    167
    +0.12
    0.01
    Negative Logits
    eca
    -0.80
    uality
    -0.75
    abouts
    -0.72
    sweet
    -0.70
    ModLoader
    -0.70
     Rib
    -0.67
    ctr
    -0.66
    IU
    -0.66
    ï¸ı
    -0.66
    eous
    -0.65
    POSITIVE LOGITS
    ized
    0.94
     readable
    0.90
     terminals
    0.88
     science
    0.86
    izable
    0.86
     interfaces
    0.83
    izes
    0.81
    anical
    0.79
    generated
    0.78
    isation
    0.78
    Activations Density 0.026%

    No Known Activations