© 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. 2402
    Prev
    Next
    INDEX
    Explanations

    the word "any"

    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
    484
    +0.13
    0.6%
    616
    +0.13
    0.6%
    436
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.13
    0.05
    616
    +0.13
    0.04
    436
    +0.09
    0.03
    Negative Logits
    rex
    -0.85
    expensive
    -0.82
    ovy
    -0.68
    efficient
    -0.68
    raid
    -0.66
    arettes
    -0.66
    romy
    -0.65
    staking
    -0.65
    esome
    -0.65
    ride
    -0.64
    POSITIVE LOGITS
    THING
    1.12
     semblance
    1.11
     conceivable
    1.06
    body
    0.92
    WHERE
    0.91
     attempt
    0.91
     possible
    0.89
     imaginable
    0.87
     lingering
    0.87
     resemblance
    0.85
    Activations Density 0.060%

    No Known Activations