© 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 24576
    9. 8-RES_FS24576-JB
    11. 18301
    Prev
    Next
    INDEX
    Explanations

    terms related to religious or spiritual contexts

    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
    288
    +0.16
    0.7%
    526
    +0.11
    0.5%
    284
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.16
    0.02
    345
    +0.11
    0.01
    288
    +0.11
    0.02
    Negative Logits
    annis
    -0.77
    OPA
    -0.77
    ocre
    -0.76
    mington
    -0.76
    err
    -0.74
    adjusted
    -0.74
    niper
    -0.73
     Hust
    -0.73
    yip
    -0.72
    ettlement
    -0.70
    POSITIVE LOGITS
     rites
    1.07
     scripture
    1.00
     cows
    0.92
     rite
    0.92
     sacred
    0.91
    ness
    0.90
     relics
    0.90
     oath
    0.90
     maiden
    0.89
     sanct
    0.89
    Activations Density 0.021%

    No Known Activations