© 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. 13950
    Prev
    Next
    INDEX
    Explanations

    phrases related to legislative actions and government initiatives being implemented

    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
    699
    +0.10
    0.5%
    718
    +0.10
    0.5%
    297
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.10
    0.09
    297
    +0.10
    0.07
    102
    +0.10
    0.08
    Negative Logits
    arta
    -0.76
     Fighters
    -0.66
    Footnote
    -0.65
    Dialogue
    -0.65
    Things
    -0.61
     Millions
    -0.59
    know
    -0.59
     Anger
    -0.58
     HAVE
    -0.58
    got
    -0.58
    POSITIVE LOGITS
     originally
    1.38
     conceived
    1.21
    hes
    1.10
     initially
    1.10
     born
    1.09
     supposed
    1.07
     designed
    1.03
     awarded
    1.03
     formerly
    1.02
     discovered
    1.01
    Activations Density 0.304%

    No Known Activations