© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 16071
    Prev
    Next
    INDEX
    Explanations

    contractions with 't

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "couldn't" indicating inability or impossibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Published
    -0.73
     populated
    -0.70
     protected
    -0.67
     Mechdragon
    -0.67
     revision
    -0.61
     encouraged
    -0.60
     guided
    -0.59
     seeded
    -0.59
     PU
    -0.58
     rewarded
    -0.58
    POSITIVE LOGITS
    't
    1.80
    ÃĥÃĤ
    0.99
    itely
    0.99
    fortunately
    0.97
    ÃŃ
    0.97
    ´
    0.92
    unn
    0.88
    iting
    0.88
    isexual
    0.86
    atio
    0.85
    Activations Density 0.048%

    No Known Activations