© 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. 1437
    Prev
    Next
    INDEX
    Explanations

    names of specific locations

    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
    447
    +0.16
    0.7%
    481
    +0.15
    0.7%
    219
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    757
    +0.16
    0.06
    224
    +0.15
    0.06
    219
    +0.11
    0.06
    Negative Logits
     digit
    -0.69
     perman
    -0.64
    inyl
    -0.63
     textual
    -0.60
    Wikipedia
    -0.57
    letter
    -0.56
     relational
    -0.56
    ronic
    -0.56
    itionally
    -0.56
    RW
    -0.55
    POSITIVE LOGITS
     airspace
    1.00
     yesterday
    0.83
     skies
    0.83
     Springs
    0.83
     tonight
    0.82
     Gardens
    0.79
     Harbor
    0.77
     Heights
    0.76
     Meadows
    0.76
     Valley
    0.74
    Activations Density 0.208%

    No Known Activations