© 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. 7658
    Prev
    Next
    INDEX
    Explanations

    phrases related to making an impact or causing a noticeable change

    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
    718
    +0.10
    0.5%
    22
    +0.10
    0.4%
    307
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.10
    0.01
    531
    +0.10
    0.01
    729
    +0.09
    0.01
    Negative Logits
     quotation
    -0.82
    ©¶æ
    -0.82
     contracted
    -0.78
     quotations
    -0.70
     diction
    -0.67
     crab
    -0.61
     faults
    -0.61
     Vog
    -0.61
     raven
    -0.60
     paraph
    -0.60
    POSITIVE LOGITS
    hole
    0.79
    elight
    0.78
    inel
    0.69
    holes
    0.69
    iveness
    0.69
    uable
    0.68
    iator
    0.67
    bernatorial
    0.66
    oola
    0.66
    ener
    0.65
    Activations Density 0.036%

    No Known Activations