© 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 49152
    9. 8-RES_FS49152-JB
    11. 37378
    Prev
    Next
    INDEX
    Explanations

    instances of the term "Car" in various contexts, indicating a focus on automotive-related subjects

    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
    484
    +0.12
    0.6%
    314
    +0.11
    0.5%
    721
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.12
    0.02
    89
    +0.11
    0.01
    103
    +0.10
    0.01
    Negative Logits
    é¾įå¥ij士
    -0.78
    naires
    -0.77
    ĨĴ
    -0.76
    ãģį
    -0.75
    ĸļ
    -0.70
     MSM
    -0.69
    EngineDebug
    -0.68
     newsp
    -0.67
    sembly
    -0.65
     BET
    -0.64
    POSITIVE LOGITS
    olina
    1.43
    negie
    1.35
    ousel
    1.27
    riage
    1.25
    rier
    1.24
    olyn
    1.19
    riers
    1.17
    oline
    1.12
    rots
    1.09
    bon
    1.07
    Activations Density 0.009%

    No Known Activations