© 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. 8730
    Prev
    Next
    INDEX
    Explanations

    phrases related to persuading or convincing someone

    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
    283
    +0.12
    0.5%
    255
    +0.11
    0.5%
    526
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.12
    0.01
    417
    +0.11
    0.02
    78
    +0.11
    0.01
    Negative Logits
    nam
    -0.76
    practice
    -0.72
    endor
    -0.70
    eworthy
    -0.70
    abytes
    -0.70
    OIL
    -0.69
    alm
    -0.69
    lain
    -0.67
    emale
    -0.66
    owment
    -0.66
    POSITIVE LOGITS
    tale
    0.90
    ingly
    0.83
     skeptics
    0.82
     convinc
    0.79
     reluctant
    0.77
     convince
    0.75
     voters
    0.73
    ments
    0.71
     policymakers
    0.70
     me
    0.70
    Activations Density 0.022%

    No Known Activations