© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14726
    Prev
    Next
    INDEX
    Explanations

    mentions of Harry Potter-related terms

    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
    +0.13
    0.6%
    384
    +0.11
    0.5%
    288
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.13
    0.01
    288
    +0.11
    0.01
    521
    +0.11
    0.01
    Negative Logits
    resp
    -0.68
    oples
    -0.65
    rikes
    -0.63
    IGN
    -0.63
    SHIP
    -0.61
    opausal
    -0.61
    vre
    -0.60
    inished
    -0.58
    itol
    -0.57
     contrad
    -0.57
    POSITIVE LOGITS
     Potter
    1.04
     Dumbledore
    0.84
    wra
    0.81
     Weasley
    0.79
     Malfoy
    0.78
    haus
    0.78
    olkien
    0.78
    boy
    0.77
     Hogwarts
    0.77
    land
    0.76
    Activations Density 0.029%

    No Known Activations