© 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. 13258
    Prev
    Next
    INDEX
    Explanations

    words related to potential and possibilities

    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
    228
    +0.09
    0.4%
    506
    +0.09
    0.4%
    712
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.09
    0.03
    712
    +0.09
    0.02
    228
    +0.09
    0.02
    Negative Logits
    ĪĴ
    -0.76
    cipline
    -0.74
     Payton
    -0.72
    creen
    -0.68
    men
    -0.67
    cise
    -0.67
    chet
    -0.66
    ulu
    -0.66
    ching
    -0.65
    onest
    -0.65
    POSITIVE LOGITS
     usefulness
    0.95
     pitfalls
    0.94
    ities
    0.93
    atility
    0.83
     hazards
    0.80
    ibilities
    0.80
     implications
    0.79
     dangers
    0.78
    izons
    0.78
     downside
    0.77
    Activations Density 0.036%

    No Known Activations