© 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. 41781
    Prev
    Next
    INDEX
    Explanations

    references to classes and class structures in programming

    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
    167
    +0.14
    0.7%
    288
    +0.12
    0.6%
    128
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    44
    +0.14
    0.01
    167
    +0.12
    0.01
    25
    +0.11
    0.01
    Negative Logits
    aukee
    -0.74
    PDATE
    -0.73
    STON
    -0.72
    OPLE
    -0.72
    andum
    -0.67
    hiba
    -0.67
    ovych
    -0.64
    yssey
    -0.63
    vernment
    -0.62
    hower
    -0.62
    POSITIVE LOGITS
    ifier
    1.39
    ifications
    1.31
    ifiers
    1.29
    ifies
    1.16
    ifying
    1.13
    ification
    1.10
    path
    1.10
    ifiable
    1.09
    classes
    1.02
    ified
    0.98
    Activations Density 0.012%

    No Known Activations