© 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. 20980
    Prev
    Next
    INDEX
    Explanations

    proper nouns or terms starting with "Un" in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "Un-" in various contexts

    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
    OPLE
    -0.80
     compens
    -0.67
     enhancement
    -0.67
     favors
    -0.61
     chase
    -0.61
     anytime
    -0.61
     aquarium
    -0.61
     Madden
    -0.61
     honors
    -0.61
     halftime
    -0.59
    POSITIVE LOGITS
    usual
    1.38
    surprisingly
    1.29
    finished
    1.25
    holy
    1.24
    sung
    1.23
    orthodox
    1.23
    cles
    1.22
    identified
    1.21
    iqueness
    1.21
    cyclopedia
    1.19
    Activations Density 0.017%

    No Known Activations