© 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. 17119
    Prev
    Next
    INDEX
    Explanations

    phrases related to contradictory statements

    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
    246
    +0.10
    0.4%
    694
    +0.09
    0.4%
    209
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.10
    0.05
    578
    +0.09
    0.04
    100
    +0.09
    0.04
    Negative Logits
    operation
    -0.63
    uration
    -0.61
     McDonnell
    -0.60
    wide
    -0.59
    pire
    -0.58
    ascus
    -0.57
    now
    -0.57
    ursive
    -0.56
     Barrett
    -0.56
     Ambro
    -0.55
    POSITIVE LOGITS
    chard
    1.20
    acles
    1.18
    nery
    1.16
    acle
    1.14
    acular
    1.13
    Else
    1.13
     whatever
    1.13
    chid
    1.08
    lando
    1.06
    gy
    1.05
    Activations Density 0.108%

    No Known Activations