© 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 3072
    9. 8-RES_FS3072-JB
    11. 264
    Prev
    Next
    INDEX
    Explanations

    mentions of community events, settings, and organizations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    99
    +0.11
    0.5%
    288
    +0.10
    0.5%
    496
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.06
    99
    +0.10
    0.04
    495
    +0.10
    0.04
    Negative Logits
    inen
    -0.77
    etr
    -0.71
    gins
    -0.69
    ners
    -0.68
    eton
    -0.68
    nit
    -0.67
    iasis
    -0.67
    cer
    -0.66
    otomy
    -0.65
    glers
    -0.64
    POSITIVE LOGITS
     cohesion
    0.94
     outreach
    0.89
     councils
    0.87
     members
    0.84
     member
    0.79
     elders
    0.76
     relations
    0.76
    wide
    0.73
     rallied
    0.71
     gathers
    0.69
    Activations Density 0.469%

    No Known Activations