© 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 12288
    9. 8-RES_FS12288-JB
    11. 1236
    Prev
    Next
    INDEX
    Explanations

    age-related numbers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    +0.19
    0.9%
    132
    +0.10
    0.5%
    693
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    693
    +0.19
    0.05
    689
    +0.10
    0.05
    260
    +0.10
    0.04
    Negative Logits
     signage
    -0.60
     repr
    -0.58
    etsk
    -0.57
     dissent
    -0.57
     subst
    -0.56
    plan
    -0.56
     contingency
    -0.56
    elist
    -0.56
     localized
    -0.56
    perse
    -0.56
    POSITIVE LOGITS
    ½
    0.99
     years
    0.94
    +.
    0.91
    yrs
    0.88
    yo
    0.88
    years
    0.86
     cents
    0.81
    mph
    0.80
    digy
    0.79
    +,
    0.79
    Activations Density 0.181%

    No Known Activations