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

    Neuronpedia

    Jacobian LensNEW
    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. 41617
    Prev
    Next
    INDEX
    Explanations

    fields of study and professional qualifications in educational 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
    314
    +0.12
    0.5%
    492
    +0.11
    0.5%
    687
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.04
    508
    +0.11
    0.03
    575
    +0.11
    0.03
    Negative Logits
    Sov
    -0.76
    é»Ĵ
    -0.72
    isSpecialOrderable
    -0.72
    psons
    -0.72
    ":[{"
    -0.71
    yip
    -0.69
    NetMessage
    -0.67
     bandwagon
    -0.66
     ransom
    -0.65
    BIP
    -0.65
    POSITIVE LOGITS
     sciences
    1.32
     psychology
    1.22
    iculture
    1.13
     mathematics
    1.12
     Psychology
    1.11
     biology
    1.11
     sociology
    1.11
     anthropology
    1.10
    engineering
    1.08
     science
    1.07
    Activations Density 0.139%

    No Known Activations