© 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. 11742
    Prev
    Next
    INDEX
    Explanations

    information related to notable events, figures, and incidents

    oai_token-act-pair · gpt-3.5-turbo

    instances of heroism in response to significant events or crises

    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
    issance
    -0.61
    é¾įåĸļ士
    -0.60
    vantage
    -0.60
    tion
    -0.60
    zens
    -0.59
    Located
    -0.59
    =-=-=-=-=-=-=-=-
    -0.59
    tions
    -0.57
    ãĤ¦ãĤ¹
    -0.57
    etheless
    -0.56
    POSITIVE LOGITS
     famously
    0.67
     JFK
    0.64
     Slate
    0.62
    otom
    0.57
     Kenya
    0.56
     Malta
    0.56
     satir
    0.56
     blogger
    0.56
     NYT
    0.56
     Mahm
    0.54
    Activations Density 1.653%

    No Known Activations