© 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 49152
    9. 8-RES_FS49152-JB
    11. 43092
    Prev
    Next
    INDEX
    Explanations

    references to the subjective experience and perception of individuals

    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
    343
    +0.10
    0.5%
    145
    +0.09
    0.4%
    203
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.10
    0.02
    404
    +0.09
    0.02
    284
    +0.08
    0.02
    Negative Logits
    ishers
    -0.74
    rought
    -0.71
    ishing
    -0.71
    ottest
    -0.71
    itness
    -0.70
    owler
    -0.70
    ished
    -0.70
    zbollah
    -0.69
    isSpecialOrderable
    -0.68
    regor
    -0.67
    POSITIVE LOGITS
    aurus
    1.00
    peed
    0.99
    CRIP
    0.97
    cular
    0.96
    pex
    0.94
    sein
    0.88
    oft
    0.86
    hee
    0.85
    etts
    0.85
    henko
    0.84
    Activations Density 0.025%

    No Known Activations