© 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 49152
    9. 8-RES_FS49152-JB
    11. 45794
    Prev
    Next
    INDEX
    Explanations

    references to astrology or astrological 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
    549
    +0.14
    0.6%
    288
    +0.14
    0.6%
    441
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.14
    0.01
    549
    +0.14
    0.01
    744
    +0.11
    0.01
    Negative Logits
     Nightmares
    -0.75
    essee
    -0.69
    BACK
    -0.69
    LOAD
    -0.68
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.63
    ãģĤ
    -0.62
    xus
    -0.61
    pmwiki
    -0.60
    ãĥ¯
    -0.60
    NES
    -0.60
    POSITIVE LOGITS
    rology
    1.20
    ral
    1.16
    rolog
    1.14
    igmat
    1.13
    rog
    1.13
    ro
    1.12
    rot
    1.10
    rob
    1.07
    reet
    1.06
    rament
    1.04
    Activations Density 0.003%

    No Known Activations