© 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. 7990
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by pronouns or nouns indicative of direction or transfer

    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
    217
    +0.12
    0.6%
    310
    +0.12
    0.5%
    282
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.12
    0.06
    310
    +0.12
    0.04
    665
    +0.10
    0.04
    Negative Logits
    natureconservancy
    -0.82
    tions
    -0.81
     Gap
    -0.68
    dn
    -0.63
    marine
    -0.62
     affili
    -0.59
    til
    -0.58
    NOT
    -0.57
    tion
    -0.57
    collar
    -0.57
    POSITIVE LOGITS
     by
    0.86
     BY
    0.82
    by
    0.77
    ãĥ¯
    0.70
    ãĥīãĥ©
    0.69
    ãĥĨãĤ£
    0.69
     Lama
    0.66
    andom
    0.66
    que
    0.66
    姫
    0.65
    Activations Density 0.215%

    No Known Activations