© 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 49152
    9. 8-RES_FS49152-JB
    11. 41675
    Prev
    Next
    INDEX
    Explanations

    names of individuals or entities associated with specific contexts

    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
    447
    +0.23
    1.1%
    709
    +0.12
    0.5%
    200
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    353
    +0.23
    0.03
    46
    +0.12
    0.03
    346
    +0.10
    0.03
    Negative Logits
     Seym
    -0.82
     pse
    -0.72
     conflic
    -0.71
     VID
    -0.69
    mel
    -0.68
     pregn
    -0.67
    lehem
    -0.67
    oard
    -0.66
    £ı
    -0.66
     citiz
    -0.66
    POSITIVE LOGITS
    's
    1.00
     himself
    0.96
    mania
    0.87
     confid
    0.87
     Productions
    0.81
     Goes
    0.81
     Himself
    0.79
    omics
    0.79
     joked
    0.78
    ites
    0.77
    Activations Density 0.110%

    No Known Activations