© 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 EvalsExportsAPI 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. 12425
    Prev
    Next
    INDEX
    Explanations

    information related to news and current events pertaining to politics and social issues

    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
    39
    +0.10
    0.5%
    117
    +0.10
    0.5%
    731
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    117
    +0.10
    0.04
    39
    +0.10
    0.04
    477
    +0.09
    0.03
    Negative Logits
    ère
    -0.70
    ilts
    -0.66
    cade
    -0.65
    igans
    -0.61
    etts
    -0.56
    ariat
    -0.56
     rehearsal
    -0.56
    ologically
    -0.55
    matter
    -0.54
    sv
    -0.54
    POSITIVE LOGITS
    Fla
    0.64
    Asset
    0.63
    anooga
    0.62
    çİĭ
    0.61
    osion
    0.59
    BuyableInstoreAndOnline
    0.56
     Cassidy
    0.56
    reality
    0.56
     Clemson
    0.55
    gdala
    0.54
    Activations Density 0.132%

    No Known Activations