© 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 24576
    9. 8-RES_FS24576-JB
    11. 8666
    Prev
    Next
    INDEX
    Explanations

    statements about decisions, success, and the process of growth

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    411
    +0.15
    0.7%
    409
    +0.11
    0.5%
    459
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    411
    +0.15
    0.07
    643
    +0.11
    0.05
    61
    +0.10
    0.06
    Negative Logits
     nonetheless
    -0.65
    Dear
    -0.59
    assador
    -0.59
     arsen
    -0.58
     nevertheless
    -0.57
     effectiveness
    -0.57
    asma
    -0.56
    MpServer
    -0.56
    larg
    -0.55
    estate
    -0.54
    POSITIVE LOGITS
     hesitate
    1.08
     disappoint
    0.94
     shy
    0.94
     forgetting
    0.79
     overlooked
    0.79
     hesitated
    0.75
     doubt
    0.74
     forget
    0.73
     wait
    0.71
     afraid
    0.70
    Activations Density 0.560%

    No Known Activations