© 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. 37227
    Prev
    Next
    INDEX
    Explanations

    filesystem paths and related directory structures

    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
    503
    +0.12
    0.5%
    373
    +0.11
    0.5%
    61
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    445
    +0.12
    0.01
    61
    +0.11
    0.01
    326
    +0.11
    0.01
    Negative Logits
    hower
    -0.70
     Kard
    -0.65
     Emin
    -0.64
     Rounds
    -0.62
     Nieto
    -0.62
    pots
    -0.62
     Six
    -0.61
     Halls
    -0.60
    rill
    -0.60
    lyak
    -0.60
    POSITIVE LOGITS
    exec
    0.84
    config
    0.83
    ctic
    0.81
    /$
    0.77
    vd
    0.77
    uments
    0.76
    ascript
    0.74
    cmd
    0.73
    usr
    0.73
    tenance
    0.72
    Activations Density 0.005%

    No Known Activations