© 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 24576
    9. 8-RES_FS24576-JB
    11. 9429
    Prev
    Next
    INDEX
    Explanations

    the name "Lo"

    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
    659
    +0.10
    0.5%
    706
    +0.10
    0.4%
    440
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.10
    0.02
    376
    +0.10
    0.01
    583
    +0.09
    0.01
    Negative Logits
    manship
    -0.96
    chell
    -0.76
    itated
    -0.74
    pillar
    -0.73
    orship
    -0.70
    EMENT
    -0.69
     Equality
    -0.68
    imental
    -0.68
    rations
    -0.66
    ienced
    -0.65
    POSITIVE LOGITS
    veland
    1.30
    zzi
    1.24
    fty
    1.17
    ppy
    1.14
    pper
    1.08
    zzle
    1.06
    ven
    1.05
    vers
    1.05
    fts
    1.00
    opy
    0.99
    Activations Density 0.015%

    No Known Activations