© 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. 5122
    Prev
    Next
    INDEX
    Explanations

    instances of words signaling uncertainty or possibility

    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
    752
    +0.14
    0.6%
    564
    +0.09
    0.4%
    354
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    128
    +0.14
    0.03
    284
    +0.09
    0.03
    398
    +0.08
    0.03
    Negative Logits
    igraph
    -0.74
    culus
    -0.74
    ipel
    -0.71
    lang
    -0.68
    Shape
    -0.66
    osterone
    -0.64
    hov
    -0.64
     Detail
    -0.64
    amination
    -0.63
     Diss
    -0.62
    POSITIVE LOGITS
     barg
    0.89
     justifies
    0.81
    requ
    0.80
     justification
    0.77
    needed
    0.77
    ItemTracker
    0.76
     unwitting
    0.73
     bribe
    0.73
     obligation
    0.73
     practicable
    0.73
    Activations Density 0.224%

    No Known Activations