© 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. 13489
    Prev
    Next
    INDEX
    Explanations

    information related to entertainment and news articles

    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
    579
    +0.11
    0.5%
    388
    +0.10
    0.5%
    45
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    388
    +0.11
    0.04
    693
    +0.10
    0.04
    99
    +0.10
    0.03
    Negative Logits
    icularly
    -0.71
    rolet
    -0.68
    staking
    -0.67
    awaru
    -0.67
    orically
    -0.63
    ophical
    -0.63
    ilant
    -0.60
    bery
    -0.60
    arial
    -0.60
    oteric
    -0.58
    POSITIVE LOGITS
    Ħ¢
    0.87
    ÃĹ
    0.85
    +,
    0.80
    nd
    0.79
    XL
    0.73
    x
    0.72
    010
    0.72
    dB
    0.72
    rd
    0.71
    800
    0.71
    Activations Density 0.111%

    No Known Activations