© 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 12288
    9. 8-RES_FS12288-JB
    11. 1747
    Prev
    Next
    INDEX
    Explanations

    words related to personal characteristics or actions of individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    242
    +0.11
    0.5%
    331
    +0.11
    0.5%
    603
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    601
    +0.11
    0.02
    242
    +0.11
    0.03
    262
    +0.10
    0.02
    Negative Logits
     sugg
    -0.74
    inqu
    -0.61
    ikk
    -0.61
    ichen
    -0.59
     Advisory
    -0.58
     Inqu
    -0.58
    kson
    -0.58
     inquiries
    -0.57
    adish
    -0.56
     undisclosed
    -0.56
    POSITIVE LOGITS
     versatility
    0.82
    formance
    0.81
     prowess
    0.76
     willingness
    0.76
     chops
    0.75
     resilience
    0.74
    png
    0.73
    ibilities
    0.71
     mercy
    0.70
     ingenuity
    0.69
    Activations Density 0.244%

    No Known Activations