© 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 24576
    9. 8-RES_FS24576-JB
    11. 22143
    Prev
    Next
    INDEX
    Explanations

    references to technical specifications and formats in the context of software or database entries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    447
    +0.10
    0.5%
    449
    +0.09
    0.5%
    55
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.10
    0.03
    314
    +0.09
    -0.01
    289
    +0.08
    0.01
    Negative Logits
     eviction
    -0.55
     divest
    -0.54
     potentially
    -0.53
     overwhelming
    -0.51
     stockpile
    -0.51
     advancement
    -0.50
     exemptions
    -0.50
     demographics
    -0.50
     aggregation
    -0.50
     binge
    -0.50
    POSITIVE LOGITS
    sic
    0.81
    ensis
    0.78
     translates
    0.63
    à
    0.62
    Ô
    0.62
    ãĤ¼ãĤ¦ãĤ¹
    0.61
    yahoo
    0.60
    SourceFile
    0.60
     Lumpur
    0.59
    $$$$
    0.58
    Activations Density 0.748%

    No Known Activations