© 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. 2226
    Prev
    Next
    INDEX
    Explanations

    phrases associated with guidance or instructions

    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
    104
    +0.13
    0.6%
    718
    +0.13
    0.6%
    528
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    104
    +0.13
    0.06
    608
    +0.13
    0.07
    718
    +0.09
    0.07
    Negative Logits
     deductions
    -0.74
     functioning
    -0.62
     deviations
    -0.61
     mistakes
    -0.61
     detached
    -0.61
     thereto
    -0.61
     withdrawals
    -0.60
     adaptations
    -0.60
     deduction
    -0.60
     retri
    -0.60
    POSITIVE LOGITS
     commemorate
    1.40
     coincide
    1.35
    pless
    1.25
     celebrate
    1.21
     accompany
    1.09
     emphasize
    1.06
     promote
    1.05
    wered
    1.02
     illustrate
    0.98
     signify
    0.98
    Activations Density 0.236%

    No Known Activations