© 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. 10031
    Prev
    Next
    INDEX
    Explanations

    sentences or statements that conclude a piece of writing

    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
    480
    +0.16
    0.7%
    6
    +0.13
    0.6%
    640
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.16
    0.10
    679
    +0.13
    0.08
    640
    +0.13
    0.07
    Negative Logits
     induct
    -0.69
     receptive
    -0.66
     bonded
    -0.65
     fist
    -0.64
     featured
    -0.64
    ailability
    -0.64
     inverse
    -0.64
     booted
    -0.63
     hammered
    -0.62
     notor
    -0.62
    POSITIVE LOGITS
     [/
    1.31
     ..."
    1.30
    [/
    1.29
     */
    1.13
    */
    1.13
    »
    1.12
     â̦"
    1.11
    >"
    1.10
     Especially
    1.09
    )"
    1.06
    Activations Density 0.284%

    No Known Activations