© 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 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. 11003
    Prev
    Next
    INDEX
    Explanations

    adjectives that express opinions or perceptions

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    218
    +0.11
    0.5%
    320
    +0.10
    0.5%
    331
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    183
    +0.11
    0.04
    242
    +0.10
    0.04
    331
    +0.10
    0.04
    Negative Logits
    itton
    -0.77
    pour
    -0.68
    probably
    -0.64
     instead
    -0.62
    instead
    -0.62
    sometimes
    -0.61
     Probably
    -0.60
    Kings
    -0.60
    rather
    -0.60
    onen
    -0.59
    POSITIVE LOGITS
     anymore
    1.47
     anywhere
    1.10
     nor
    1.06
     anything
    0.99
     any
    0.99
     slightest
    0.97
     necessarily
    0.95
     bothered
    0.90
     whatsoever
    0.87
    yet
    0.85
    Activations Density 0.167%

    No Known Activations