© 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. 13792
    Prev
    Next
    INDEX
    Explanations

    contractions of "is not" with a strong emphasis on "isn't" rather than "isn't"

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases indicating the absence of something

    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
    usa
    -0.61
     lame
    -0.53
    icably
    -0.52
     wound
    -0.51
     relic
    -0.50
     clue
    -0.49
     rabbit
    -0.48
     groom
    -0.48
     juven
    -0.48
     totem
    -0.48
    POSITIVE LOGITS
    _(
    0.57
    verage
    0.56
    meier
    0.56
    rosso
    0.55
    arger
    0.54
    ester
    0.53
    bleacher
    0.53
    meric
    0.53
    enei
    0.52
    Express
    0.52
    Activations Density 0.202%

    No Known Activations