© 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. 18648
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, specifically "Brown" in this context

    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
    314
    +0.14
    0.6%
    459
    +0.12
    0.6%
    495
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.14
    0.02
    376
    +0.12
    0.02
    495
    +0.11
    0.02
    Negative Logits
    PsyNetMessage
    -0.83
    Lex
    -0.79
    olated
    -0.76
    isSpecialOrderable
    -0.73
    udeau
    -0.73
    olkien
    -0.69
    oldemort
    -0.69
    uador
    -0.69
    ITAL
    -0.68
    ngth
    -0.67
    POSITIVE LOGITS
    lee
    1.16
    coat
    1.02
    ells
    0.96
    stein
    0.95
    beard
    0.92
    horn
    0.91
    ing
    0.91
    ell
    0.90
    low
    0.89
    erton
    0.86
    Activations Density 0.013%

    No Known Activations