© 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. 37332
    Prev
    Next
    INDEX
    Explanations

    descriptions of various environmental conditions and settings

    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
    +0.18
    0.8%
    460
    +0.17
    0.8%
    317
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.18
    0.05
    724
    +0.17
    0.04
    288
    +0.11
    0.04
    Negative Logits
    ameless
    -0.69
    apego
    -0.65
    escription
    -0.64
    aeper
    -0.63
    Scan
    -0.63
    Owner
    -0.63
    Accessory
    -0.62
    tsy
    -0.61
    omical
    -0.61
    secret
    -0.61
    POSITIVE LOGITS
     (>
    1.00
     environments
    0.96
     surrounded
    0.92
     alike
    0.86
     (<
    0.83
    vironments
    0.78
     plagued
    0.77
     climates
    0.75
     situations
    0.75
     where
    0.75
    Activations Density 0.139%

    No Known Activations