© 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. 9330
    Prev
    Next
    INDEX
    Explanations

    items related to giveaways or promotions

    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
    314
    +0.18
    0.9%
    442
    +0.14
    0.7%
    627
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.18
    0.01
    160
    +0.14
    0.05
    442
    +0.13
    0.04
    Negative Logits
     metic
    -0.81
     Polk
    -0.80
     Tier
    -0.73
     ALEC
    -0.73
     LAW
    -0.72
     PowerShell
    -0.71
     Poll
    -0.70
     Dent
    -0.70
     COVER
    -0.70
     IPM
    -0.70
    POSITIVE LOGITS
    d
    1.55
    sb
    1.49
    h
    1.48
    n
    1.46
    b
    1.45
    f
    1.45
    r
    1.43
    c
    1.42
    dx
    1.40
    t
    1.40
    Activations Density 0.189%

    No Known Activations