© 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. 11-RES-JB
    11. 6276
    Prev
    Next
    INDEX
    Explanations

    phrases related to long-term planning or consequences

    oai_token-act-pair · gpt-3.5-turbo

    references to long-term considerations or impacts

    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
     Cosponsors
    -0.95
    ©¶æ¥µ
    -0.94
    asty
    -0.75
    riad
    -0.70
    gyn
    -0.70
    girls
    -0.70
    chy
    -0.69
    xtap
    -0.69
    kas
    -0.68
     Godd
    -0.68
    POSITIVE LOGITS
     viability
    1.03
     unemployed
    1.01
     sustainability
    0.94
     rentals
    0.90
     memory
    0.89
     outlook
    0.87
     stability
    0.85
     survival
    0.84
     planning
    0.84
     ramifications
    0.83
    Activations Density 0.054%

    No Known Activations