© 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. 9-RES-JB
    11. 11335
    Prev
    Next
    INDEX
    Explanations

    phrases containing the expression "such thing"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference the non-existence of certain concepts or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OIL
    -0.63
    emen
    -0.59
     excerpts
    -0.57
    CDC
    -0.57
    glers
    -0.57
    ockets
    -0.57
     Cumm
    -0.56
    xtap
    -0.55
    ickets
    -0.55
     Banks
    -0.53
    POSITIVE LOGITS
     thing
    0.79
    bidden
    0.75
    inction
    0.73
    ileged
    0.67
    thing
    0.66
    ignty
    0.65
     Deity
    0.64
     Thing
    0.62
    zee
    0.61
    idable
    0.61
    Activations Density 0.076%

    No Known Activations