© 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. 10-RES-JB
    11. 19084
    Prev
    Next
    INDEX
    Explanations

    statements indicating importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating signs of progress or significant indicators within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     captcha
    -0.82
    ãĤ¦ãĤ¹
    -0.71
    iaries
    -0.69
    ade
    -0.69
    iHUD
    -0.68
    »Ĵ
    -0.68
    ades
    -0.66
    kson
    -0.65
    hari
    -0.64
    ãĤ´ãĥ³
    -0.64
    POSITIVE LOGITS
     appreciation
    1.13
     solidarity
    1.08
     desperation
    1.07
     toughness
    1.06
     respect
    1.06
     gratitude
    1.05
     strength
    1.04
     displeasure
    1.03
     disrespect
    1.03
     defiance
    1.03
    Activations Density 0.144%

    No Known Activations