© 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. 8520
    Prev
    Next
    INDEX
    Explanations

    terms related to technology tools and software programs

    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
    323
    +0.12
    0.6%
    314
    +0.10
    0.4%
    527
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.12
    0.02
    103
    +0.10
    0.02
    48
    +0.09
    0.02
    Negative Logits
     detail
    -0.63
     observer
    -0.63
     synergy
    -0.60
     lump
    -0.60
     visitor
    -0.58
     colleg
    -0.57
     pigeon
    -0.57
     Pengu
    -0.57
     predis
    -0.56
     clipping
    -0.56
    POSITIVE LOGITS
    ±
    1.12
    Ö¼
    1.03
    ´
    0.94
    ¿
    0.93
    ¦
    0.93
    ¶
    0.92
    ¤
    0.91
    Ã
    0.91
    ÃĽ
    0.89
    Ĩ
    0.89
    Activations Density 0.042%

    No Known Activations