© 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. 22540
    Prev
    Next
    INDEX
    Explanations

    phrases related to achievement and progress

    oai_token-act-pair · gpt-4o-miniTriggered 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
    530
    +0.09
    0.4%
    181
    +0.09
    0.4%
    745
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    298
    +0.09
    0.03
    530
    +0.09
    0.02
    750
    +0.09
    0.02
    Negative Logits
     alone
    -0.73
    sbm
    -0.64
     sake
    -0.64
     arose
    -0.59
     accompanies
    -0.58
    oir
    -0.57
    Cola
    -0.56
    ek
    -0.56
     preceded
    -0.56
     betrayed
    -0.56
    POSITIVE LOGITS
     conclusion
    1.25
     milestone
    1.14
     heights
    1.09
     climax
    1.08
     plateau
    1.06
     threshold
    1.06
     pinnacle
    1.03
     conclusions
    1.03
     halfway
    1.02
     milestones
    0.99
    Activations Density 0.127%

    No Known Activations