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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 22458
    Prev
    Next
    INDEX
    Explanations

    phrases that describe conditions or situations with varying levels of severity or complexity

    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
    22
    +0.12
    0.5%
    400
    +0.09
    0.4%
    362
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.12
    0.06
    210
    +0.09
    0.04
    122
    +0.09
    0.04
    Negative Logits
    avers
    -0.87
    actionDate
    -0.85
    ixel
    -0.82
    aders
    -0.77
    sers
    -0.76
    ixels
    -0.76
    verbs
    -0.75
    ipedia
    -0.74
    isson
    -0.74
    adows
    -0.73
    POSITIVE LOGITS
     manner
    0.80
     basis
    0.77
     contingent
    0.77
     existence
    0.77
     presence
    0.77
     ways
    0.76
     combination
    0.75
     incarnation
    0.73
     iteration
    0.71
     versions
    0.71
    Activations Density 0.290%

    No Known Activations