© 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 49152
    9. 8-RES_FS49152-JB
    11. 45789
    Prev
    Next
    INDEX
    Explanations

    specific references to substances or elements associated with health, crime, or personal items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    447
    +0.51
    3.3%
    481
    +0.29
    1.9%
    480
    +0.24
    1.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.51
    0.12
    266
    +0.29
    0.09
    480
    +0.24
    0.03
    Negative Logits
     Niet
    -0.52
     predec
    -0.48
     Democr
    -0.48
    oppable
    -0.47
     undermin
    -0.47
     Vaugh
    -0.45
    Ire
    -0.45
    Topics
    -0.44
     advoc
    -0.42
    senal
    -0.42
    POSITIVE LOGITS
     âĢº
    0.55
    ¶
    0.55
    weed
    0.47
    ↵
    0.45
    ?
    0.44
     âĢ¢
    0.43
    ↵↵
    0.43
    ↵Âł
    0.42
     ][
    0.42
    /(
    0.42
    Activations Density 0.692%

    No Known Activations