© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23978
    Prev
    Next
    INDEX
    Explanations

    conjunctions or clauses that express cause and effect

    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
    393
    +0.14
    0.6%
    583
    +0.12
    0.5%
    481
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    601
    +0.14
    0.04
    705
    +0.12
    0.04
    583
    +0.10
    0.03
    Negative Logits
    oses
    -0.72
    ographs
    -0.67
    rack
    -0.66
    uct
    -0.66
    uner
    -0.64
    ãĥ¬
    -0.63
    osures
    -0.59
    uli
    -0.59
    idia
    -0.58
    sid
    -0.57
    POSITIVE LOGITS
     there
    0.86
     we
    0.78
     they
    0.77
     whoever
    0.76
    eday
    0.73
     although
    0.72
     despite
    0.68
     mankind
    0.67
     THERE
    0.66
    cher
    0.66
    Activations Density 0.129%

    No Known Activations