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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 41784
    Prev
    Next
    INDEX
    Explanations

    words related to religion or religious concepts

    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
    543
    +0.12
    0.5%
    373
    +0.10
    0.5%
    101
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.01
    639
    +0.10
    0.01
    659
    +0.10
    0.01
    Negative Logits
     Slate
    -0.71
    Magikarp
    -0.67
     IMAGES
    -0.62
     [+
    -0.61
    romeda
    -0.60
    BALL
    -0.59
     insensitive
    -0.57
     pixel
    -0.57
    /-
    -0.57
     monop
    -0.56
    POSITIVE LOGITS
    ativity
    0.98
    iosity
    0.85
    gency
    0.82
    owship
    0.80
    MpServer
    0.79
    amped
    0.76
    idation
    0.72
    itual
    0.71
    ubric
    0.71
    ped
    0.71
    Activations Density 0.010%

    No Known Activations