© 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. 26694
    Prev
    Next
    INDEX
    Explanations

    verbs and actions related to choices and consequences

    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
    314
    +0.10
    0.5%
    595
    +0.10
    0.4%
    738
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    738
    +0.10
    0.03
    184
    +0.10
    0.02
    570
    +0.09
    0.01
    Negative Logits
     FANT
    -0.60
    ixties
    -0.60
     swell
    -0.59
     understands
    -0.58
     perv
    -0.57
    roma
    -0.56
     (%
    -0.54
     Bruins
    -0.54
     beh
    -0.53
     rightly
    -0.53
    POSITIVE LOGITS
     altogether
    0.99
     oneself
    0.85
    irtual
    0.79
    gans
    0.78
    quished
    0.78
     yourself
    0.78
     versa
    0.75
    ivably
    0.74
     outright
    0.73
    éŃĶ
    0.72
    Activations Density 0.145%

    No Known Activations