© 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. 37282
    Prev
    Next
    INDEX
    Explanations

    pointers and their dereferencing in programming contexts

    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
    373
    +0.10
    0.5%
    692
    +0.10
    0.4%
    754
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.01
    42
    +0.10
    0.01
    699
    +0.10
    0.01
    Negative Logits
    uador
    -0.80
    quickShipAvailable
    -0.73
    ruary
    -0.73
     Chamberlain
    -0.71
     Mayhem
    -0.71
     Wim
    -0.69
     Tayyip
    -0.68
    arily
    -0.67
     Yel
    -0.66
    ulence
    -0.66
    POSITIVE LOGITS
    src
    0.91
    tmp
    0.81
    ptr
    0.79
    buf
    0.78
    capt
    0.77
    STD
    0.75
    (*
    0.75
    pent
    0.75
    pend
    0.72
    bp
    0.72
    Activations Density 0.010%

    No Known Activations