© 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. 18625
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "man" in the context of different situations and dialogues

    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
    515
    +0.13
    0.6%
    291
    +0.11
    0.5%
    247
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    515
    +0.13
    0.04
    291
    +0.11
    0.04
    247
    +0.10
    0.03
    Negative Logits
    PsyNetMessage
    -0.83
     Cosponsors
    -0.69
    ython
    -0.67
     Pwr
    -0.65
    EStreamFrame
    -0.64
    Import
    -0.62
    TING
    -0.62
     Neighborhood
    -0.62
     inclusion
    -0.62
    Analysis
    -0.59
    POSITIVE LOGITS
    gling
    1.29
    nered
    1.24
    hood
    1.19
    uscript
    1.14
    hunt
    1.14
    hattan
    1.08
    oeuv
    1.06
    osphere
    1.05
    ifest
    1.00
    handled
    0.99
    Activations Density 0.062%

    No Known Activations