© 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 12288
    5. 8-RES_FS12288-JB
    6. 1727
    Prev
    Next
    INDEX
    Explanations

    websites and links

    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
    114
    +0.10
    0.4%
    145
    +0.09
    0.4%
    39
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    586
    +0.10
    0.04
    114
    +0.09
    0.04
    39
    +0.09
    0.04
    Negative Logits
     Parenthood
    -0.73
     magnitude
    -0.67
     progress
    -0.65
     caucuses
    -0.63
     doubling
    -0.62
     Goldberg
    -0.62
    ĪĴ
    -0.62
     lockout
    -0.61
     damaging
    -0.60
     nationally
    -0.59
    POSITIVE LOGITS
    /?
    1.56
    /#
    1.40
    /,
    1.32
    /)
    1.23
    /.
    1.20
    /-
    1.11
    /_
    1.10
    cdn
    1.01
    /
    0.99
     âĢº
    0.94
    Activations Density 0.067%

    No Known Activations