© 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. 16670
    Prev
    Next
    INDEX
    Explanations

    official titles or positions, particularly in government or law enforcement

    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
    496
    +0.11
    0.5%
    314
    +0.11
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.04
    574
    +0.11
    0.03
    508
    +0.10
    0.03
    Negative Logits
    ifiers
    -0.70
     captcha
    -0.69
    igraph
    -0.67
    864
    -0.61
    plings
    -0.60
    oxide
    -0.60
     streak
    -0.59
     multit
    -0.59
     bets
    -0.59
     offline
    -0.58
    POSITIVE LOGITS
     Minister
    1.59
     Dept
    1.41
     Department
    1.40
     Secretary
    1.39
     Ministry
    1.38
     Commissioner
    1.21
     minister
    1.16
     secretary
    1.16
     Directorate
    1.06
     Bureau
    1.05
    Activations Density 0.114%

    No Known Activations