© 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. 13058
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns

    oai_token-act-pair · gpt-3.5-turbo

    expressions of self-identification and personal assertions

    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
    advertisement
    -0.79
    Mech
    -0.73
    ãĥĥãĥī
    -0.72
     Georgian
    -0.63
     Hilbert
    -0.61
    Pont
    -0.61
    Reviewer
    -0.60
    Translation
    -0.60
    Marginal
    -0.60
     toget
    -0.59
    POSITIVE LOGITS
    'm
    1.81
     am
    1.56
    've
    1.17
     intend
    1.12
    'll
    1.10
     owe
    0.99
     want
    0.97
     adore
    0.96
     refuse
    0.95
     wanna
    0.94
    Activations Density 0.283%

    No Known Activations