© 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. 1661
    Prev
    Next
    INDEX
    Explanations

    phrases indicating positive performance or successful beginnings

    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
    373
    +0.18
    0.9%
    242
    +0.10
    0.5%
    294
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.18
    0.02
    373
    +0.10
    -0.01
    242
    +0.09
    0.01
    Negative Logits
    ICLE
    -0.64
     persisted
    -0.59
    insured
    -0.58
     proble
    -0.57
    CVE
    -0.56
    enance
    -0.56
    paralle
    -0.56
    izo
    -0.55
    likely
    -0.55
     autom
    -0.55
    POSITIVE LOGITS
    addle
    0.70
    oots
    0.65
    fen
    0.65
     Siberia
    0.62
     explore
    0.62
    \\\\\\\\
    0.62
    BuyableInstoreAndOnline
    0.61
    istered
    0.61
    ctic
    0.61
    ousy
    0.61
    Activations Density 0.066%

    No Known Activations