© 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. 1494
    Prev
    Next
    INDEX
    Explanations

    names of individuals or specific entities

    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
    526
    +0.12
    0.5%
    90
    +0.11
    0.5%
    45
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    511
    +0.12
    0.01
    316
    +0.11
    0.01
    284
    +0.09
    0.01
    Negative Logits
    %:
    -0.65
    hart
    -0.65
    rylic
    -0.63
    iatrics
    -0.61
    xious
    -0.61
     NIC
    -0.60
     CARE
    -0.59
    ware
    -0.58
    ghai
    -0.57
     Helpful
    -0.57
    POSITIVE LOGITS
    clerosis
    1.09
    heet
    1.04
    ourced
    0.92
    aurus
    0.91
    ourcing
    0.90
    ions
    0.87
    ources
    0.87
    ophical
    0.86
    atile
    0.83
    lav
    0.83
    Activations Density 0.024%

    No Known Activations