© 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. 22484
    Prev
    Next
    INDEX
    Explanations

    terms related to acquiring and achieving something, particularly in the context of power or resources

    oai_token-act-pair · gpt-4o-miniTriggered 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
    271
    +0.11
    0.5%
    420
    +0.11
    0.5%
    604
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.11
    0.03
    271
    +0.11
    0.02
    604
    +0.10
    0.02
    Negative Logits
    sis
    -0.72
    iso
    -0.71
    azo
    -0.66
     kidding
    -0.62
     molecule
    -0.62
     contemplated
    -0.60
     crying
    -0.59
    opus
    -0.59
     solicitation
    -0.58
    mate
    -0.56
    POSITIVE LOGITS
     notoriety
    1.15
     traction
    1.09
    esville
    1.03
     access
    0.96
     momentum
    0.92
     insight
    0.92
     prominence
    0.92
    iculty
    0.86
     insights
    0.84
     visibility
    0.81
    Activations Density 0.025%

    No Known Activations