© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 41523
    Prev
    Next
    INDEX
    Explanations

    mentions of the state of Nebraska

    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
    99
    +0.12
    0.6%
    288
    +0.11
    0.5%
    598
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    11
    +0.12
    0.01
    53
    +0.11
    0.01
    224
    +0.11
    0.01
    Negative Logits
    ially
    -0.82
    allery
    -0.79
    iating
    -0.77
    IAL
    -0.76
    eatures
    -0.72
    */(
    -0.71
    isations
    -0.70
    izations
    -0.68
    ials
    -0.68
    ãĥ£
    -0.68
    POSITIVE LOGITS
     Omaha
    0.95
     Nebraska
    0.93
    braska
    0.90
     Wesley
    0.90
     Instruments
    0.82
    boro
    0.82
     Cheese
    0.80
    ucky
    0.78
     Springs
    0.73
    icut
    0.71
    Activations Density 0.003%

    No Known Activations