© 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. 14489
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a definitive answer or conclusion

    oai_token-act-pair · gpt-3.5-turbo

    phrases that assert the correctness or incorrectness of answers to questions

    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
    vre
    -0.73
    ENDED
    -0.71
    models
    -0.71
    ventures
    -0.67
    =~=~
    -0.66
    pecting
    -0.64
    aired
    -0.64
    icipated
    -0.64
    usp
    -0.64
    astical
    -0.64
    POSITIVE LOGITS
     unequiv
    1.17
     yes
    1.15
     YES
    1.08
     affirmative
    1.00
     simple
    0.99
     emph
    0.99
     obvious
    0.99
     straightforward
    0.93
     unamb
    0.90
     unmist
    0.82
    Activations Density 0.101%

    No Known Activations