© 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. 41570
    Prev
    Next
    INDEX
    Explanations

    instances of the word "find" across various contexts

    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
    500
    +0.10
    0.4%
    195
    +0.10
    0.4%
    375
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    429
    +0.10
    0.02
    604
    +0.10
    0.02
    500
    +0.09
    0.02
    Negative Logits
    assisted
    -0.75
    ansky
    -0.73
    agn
    -0.71
    stroke
    -0.67
    inion
    -0.67
    forming
    -0.65
    jab
    -0.65
    awar
    -0.64
    haw
    -0.63
    idium
    -0.62
    POSITIVE LOGITS
     plenty
    1.06
     yourself
    0.87
     yourselves
    0.86
     lots
    0.82
     ample
    0.81
     references
    0.79
     traces
    0.78
     them
    0.77
     fewer
    0.75
     ourselves
    0.74
    Activations Density 0.029%

    No Known Activations