© 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 EvalsExportsAPI 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. 12507
    Prev
    Next
    INDEX
    Explanations

    mentions of rock and roll music and 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
    337
    +0.12
    0.6%
    687
    +0.10
    0.5%
    546
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    398
    +0.12
    0.03
    482
    +0.10
    0.03
    188
    +0.09
    0.02
    Negative Logits
    ħĭ
    -0.79
     Marketable
    -0.79
    aez
    -0.76
    ãĥĥãĥī
    -0.74
    overe
    -0.68
    */(
    -0.62
    INAL
    -0.60
    ²¾
    -0.60
    actionDate
    -0.60
     defect
    -0.59
    POSITIVE LOGITS
    lake
    0.79
    bows
    0.73
    African
    0.72
    wagen
    0.66
    ÅĤ
    0.65
     Mountain
    0.65
    velt
    0.63
    water
    0.63
    coe
    0.63
     Gibraltar
    0.63
    Activations Density 0.087%

    No Known Activations