© 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. 11376
    Prev
    Next
    INDEX
    Explanations

    mentions of vans in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "van."

    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
    pta
    -0.86
    ometimes
    -0.73
    mercial
    -0.70
    ĪĴ
    -0.68
    ippi
    -0.66
     reluct
    -0.64
    MpServer
    -0.61
    DonaldTrump
    -0.61
    ĺħ
    -0.61
     rites
    -0.60
    POSITIVE LOGITS
     Hels
    0.92
    neys
    0.86
    adium
    0.84
    ques
    0.83
    quished
    0.81
    illa
    0.80
    ney
    0.78
     Gaal
    0.78
    ishes
    0.78
    rol
    0.75
    Activations Density 0.022%

    No Known Activations