© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 18854
    Prev
    Next
    INDEX
    Explanations

    statements of fact or specific information

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating the presence or absence of issues or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fuck
    -0.85
    stars
    -0.79
     clich
    -0.77
     evils
    -0.72
     Characters
    -0.71
     tits
    -0.69
     metaphors
    -0.69
     sucks
    -0.67
     fuck
    -0.65
     desserts
    -0.65
    POSITIVE LOGITS
    currently
    1.08
     widespread
    1.05
     speculation
    0.97
     ongoing
    0.97
     disagreement
    0.95
     ample
    0.94
    stantial
    0.93
     evidence
    0.92
     no
    0.90
     extensive
    0.89
    Activations Density 0.143%

    No Known Activations