© 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. 6843
    Prev
    Next
    INDEX
    Explanations

    descriptive details about specific types of food ingredients and products

    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
    481
    +0.16
    0.7%
    232
    +0.11
    0.5%
    6
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.16
    0.06
    6
    +0.11
    0.05
    308
    +0.11
    0.03
    Negative Logits
     disg
    -0.84
     carbohyd
    -0.78
     deleg
    -0.76
     warr
    -0.76
     skilled
    -0.74
     referen
    -0.74
     arsen
    -0.70
     toler
    -0.70
     destro
    -0.69
     conflic
    -0.68
    POSITIVE LOGITS
    !,
    1.28
     Syndrome
    1.25
    âĦ¢
    1.25
     Again
    1.18
     Forever
    1.16
     Productions
    1.13
    !.
    1.07
    !:
    1.04
     Remastered
    1.04
    ?,
    1.01
    Activations Density 0.262%

    No Known Activations