© 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. 37203
    Prev
    Next
    INDEX
    Explanations

    terms related to obligations and licensing

    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
    566
    +0.14
    0.7%
    263
    +0.12
    0.6%
    84
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.14
    0.01
    404
    +0.12
    0.01
    107
    +0.12
    0.01
    Negative Logits
     Nadu
    -0.73
     Sands
    -0.70
     Anthem
    -0.67
    ioxide
    -0.66
     Fired
    -0.64
    ORN
    -0.64
     Norn
    -0.63
     Leopard
    -0.62
    Jet
    -0.62
     Institutes
    -0.62
    POSITIVE LOGITS
    İ
    1.26
    Ĵ
    1.23
    Ģ
    1.16
    Į
    1.13
    İĭ
    1.12
    ª
    1.06
    £
    1.05
    ı
    1.03
    §
    1.03
    ĵ
    1.02
    Activations Density 0.004%

    No Known Activations