© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 41511
    Prev
    Next
    INDEX
    Explanations

    mentions of consensus

    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
    314
    +0.12
    0.5%
    715
    +0.10
    0.4%
    229
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    229
    +0.12
    0.01
    345
    +0.10
    0.01
    715
    +0.09
    0.01
    Negative Logits
     Hoover
    -0.74
    WOOD
    -0.73
     Meadow
    -0.70
     ECO
    -0.68
     Ames
    -0.67
     Weir
    -0.66
     clearance
    -0.66
     Wast
    -0.66
     Kurd
    -0.65
     Wem
    -0.64
    POSITIVE LOGITS
    piracy
    1.57
    ervatives
    1.52
    umers
    1.46
    ensus
    1.40
    istent
    1.35
    cientious
    1.35
    ensual
    1.35
    olid
    1.32
    idered
    1.31
    erv
    1.30
    Activations Density 0.005%

    No Known Activations