© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14472
    Prev
    Next
    INDEX
    Explanations

    instructions or steps in a recipe

    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
    640
    +0.25
    1.2%
    160
    +0.13
    0.6%
    442
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.25
    0.07
    160
    +0.13
    0.05
    6
    +0.10
    0.05
    Negative Logits
     amph
    -0.91
     parad
    -0.82
     intent
    -0.79
     ambassadors
    -0.75
     sten
    -0.74
     imperson
    -0.70
     painting
    -0.69
     pupp
    -0.69
     carving
    -0.67
     puberty
    -0.67
    POSITIVE LOGITS
    Total
    1.41
    Average
    1.40
    Ranked
    1.22
    total
    1.17
    Overall
    1.15
    Avg
    1.15
    Number
    1.14
    Percent
    1.14
    Maximum
    1.11
    Population
    1.06
    Activations Density 0.152%

    No Known Activations