© 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 EvalsExportsAPI 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. 6-RES-JB
    11. 13859
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to a specific capitalized term, "Cap"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Cap" or variations thereof, likely focusing on a specific context or entity related to that term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hower
    -0.94
    ĪĴ
    -0.93
     silence
    -0.79
    perse
    -0.78
    ¿½
    -0.75
    selves
    -0.70
     td
    -0.69
     directional
    -0.69
     anten
    -0.68
    Reloaded
    -0.68
    POSITIVE LOGITS
    itol
    1.29
    itals
    1.20
    illary
    1.14
    acity
    1.10
    rice
    1.04
    aic
    1.04
    rices
    1.00
    abilities
    1.00
    aign
    0.97
    uchin
    0.96
    Activations Density 0.014%

    No Known Activations