© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 22216
    Prev
    Next
    INDEX
    Explanations

    expressions of realization or understanding

    oai_token-act-pair · gpt-4o-miniTriggered 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
    240
    +0.11
    0.5%
    28
    +0.10
    0.5%
    679
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    750
    +0.11
    0.04
    213
    +0.10
    0.03
    510
    +0.10
    0.03
    Negative Logits
    umbn
    -0.73
    pmwiki
    -0.70
    Dialogue
    -0.70
    bis
    -0.67
    ulo
    -0.67
    utic
    -0.66
    onto
    -0.66
    ributes
    -0.65
    esc
    -0.64
    iddled
    -0.63
    POSITIVE LOGITS
     beforehand
    1.10
     sooner
    0.71
     yesterday
    0.70
     initially
    0.69
     earlier
    0.68
     doubted
    0.66
     existed
    0.66
     originally
    0.65
     Ukrain
    0.64
    saw
    0.63
    Activations Density 0.139%

    No Known Activations