© 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. 20881
    Prev
    Next
    INDEX
    Explanations

    mentions of news headlines or organizations

    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
    373
    +0.15
    0.7%
    383
    +0.10
    0.5%
    634
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    208
    +0.15
    0.02
    634
    +0.10
    0.02
    690
    +0.10
    0.02
    Negative Logits
    ocene
    -0.66
    dies
    -0.65
    plates
    -0.63
    conservancy
    -0.63
    grades
    -0.62
    ¯
    -0.59
     myster
    -0.59
    cephal
    -0.58
    sed
    -0.58
    pell
    -0.57
    POSITIVE LOGITS
    Money
    0.98
    ILLE
    0.76
    Politics
    0.73
    )—
    0.72
    agascar
    0.72
    News
    0.72
    )--
    0.71
     affiliate
    0.66
    NEWS
    0.65
     Philippines
    0.65
    Activations Density 0.016%

    No Known Activations