© 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. 7566
    Prev
    Next
    INDEX
    Explanations

    spoken or written statements given by spokespersons or representatives of organizations

    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
    745
    +0.12
    0.6%
    21
    +0.11
    0.5%
    446
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.12
    0.06
    121
    +0.11
    0.05
    69
    +0.11
    0.03
    Negative Logits
     pioneers
    -0.70
     slaughter
    -0.68
     pitted
    -0.68
     Jury
    -0.65
     injust
    -0.65
     mortg
    -0.64
     Reincarn
    -0.63
    Exper
    -0.63
     punk
    -0.62
     killers
    -0.61
    POSITIVE LOGITS
     spokeswoman
    1.10
     spokesman
    1.04
    onse
    1.01
     spokesperson
    0.99
     emailed
    0.98
     declined
    0.98
     clarification
    0.94
     spokes
    0.90
     statement
    0.84
     clarified
    0.83
    Activations Density 0.304%

    No Known Activations