© 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. 37357
    Prev
    Next
    INDEX
    Explanations

    elements and compounds related to minerals and chemical substances

    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
    +0.10
    0.5%
    25
    +0.10
    0.5%
    712
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.01
    99
    +0.10
    0.01
    381
    +0.09
    0.01
    Negative Logits
    sung
    -0.83
    fare
    -0.81
    alez
    -0.81
    rors
    -0.80
    lass
    -0.79
    psc
    -0.77
    itized
    -0.77
    sein
    -0.75
    gery
    -0.74
    cock
    -0.73
    POSITIVE LOGITS
     phosphate
    1.02
     chloride
    1.00
     calcium
    0.87
     iod
    0.84
     magnesium
    0.77
     phosphorus
    0.75
     ions
    0.75
     aqu
    0.73
     oxide
    0.73
     sulf
    0.73
    Activations Density 0.009%

    No Known Activations