© 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. 17409
    Prev
    Next
    INDEX
    Explanations

    conjunctions followed by opinions or statements about plans and predictions

    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
    373
    +0.12
    0.5%
    203
    +0.10
    0.5%
    679
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.12
    0.05
    208
    +0.10
    0.04
    483
    +0.10
    0.04
    Negative Logits
    âĶĢâĶĢâĶĢâĶĢ
    -0.71
    itor
    -0.70
    âĹ¼
    -0.69
    erver
    -0.67
    tail
    -0.65
    ById
    -0.64
    seless
    -0.64
    utic
    -0.64
    par
    -0.64
    obyl
    -0.63
    POSITIVE LOGITS
     suffice
    1.42
     anecd
    1.21
     nevertheless
    1.00
     nonetheless
    0.97
     indications
    0.95
     anecdotal
    0.85
     guesses
    0.82
     hopefully
    0.74
     circumst
    0.73
     estimates
    0.73
    Activations Density 0.136%

    No Known Activations