© 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. 41776
    Prev
    Next
    INDEX
    Explanations

    terms related to emotional intelligence and its implications

    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
    +0.11
    0.5%
    459
    +0.11
    0.5%
    213
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.11
    0.06
    592
    +0.11
    0.04
    288
    +0.10
    0.06
    Negative Logits
    uminati
    -0.81
    ointed
    -0.76
     NRL
    -0.69
     Plymouth
    -0.69
    20439
    -0.67
     Thom
    -0.65
     Helen
    -0.63
     Ashes
    -0.60
     Christy
    -0.60
    ammy
    -0.60
    POSITIVE LOGITS
     itself
    1.06
     behaves
    1.04
     represents
    1.04
     exists
    1.03
     cannot
    1.00
     becomes
    1.00
     tends
    0.99
     satisfies
    0.97
     lacks
    0.97
     occupies
    0.97
    Activations Density 0.229%

    No Known Activations