© 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. 24217
    Prev
    Next
    INDEX
    Explanations

    critical phrases related to essential experiences or events

    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
    481
    +0.31
    1.4%
    388
    +0.10
    0.5%
    224
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.31
    0.09
    575
    +0.10
    0.08
    481
    +0.10
    0.08
    Negative Logits
    yss
    -0.69
     cumulative
    -0.62
     specificity
    -0.58
    uez
    -0.57
     "$:/
    -0.56
    organ
    -0.56
    azard
    -0.55
    verning
    -0.54
    aer
    -0.53
    anwhile
    -0.53
    POSITIVE LOGITS
     someday
    0.95
     anytime
    0.90
     ASAP
    0.89
     sometime
    0.81
    ?????
    0.80
    ???
    0.75
    !?
    0.75
    ?
    0.75
     instead
    0.74
     sooner
    0.74
    Activations Density 0.838%

    No Known Activations