© 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. 11-RES-JB
    11. 7441
    Prev
    Next
    INDEX
    Explanations

    explicit disclaimers in a text

    oai_token-act-pair · gpt-3.5-turbo

    assertions of opinion or truthfulness related to content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rants
    -0.70
    colm
    -0.70
    vati
    -0.70
    eness
    -0.67
    Roberts
    -0.66
    worthiness
    -0.66
    luaj
    -0.65
    LOS
    -0.65
    racuse
    -0.63
    hung
    -0.63
    POSITIVE LOGITS
     approximate
    1.07
     unofficial
    1.03
     NOT
    1.01
     purely
    0.99
     subjective
    0.98
     tentative
    0.97
     fictitious
    0.95
     provisional
    0.94
     strictly
    0.91
     preliminary
    0.91
    Activations Density 0.191%

    No Known Activations