© 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. 8-RES-JB
    11. 12312
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person or character named "Tion"

    oai_token-act-pair · gpt-3.5-turbo

    suffixed forms of the word "ion," indicating concepts related to processes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.83
    herty
    -0.75
     unbeliev
    -0.71
    ramid
    -0.70
    ultz
    -0.68
    RESULTS
    -0.66
    isSpecialOrderable
    -0.65
     gobl
    -0.65
    raction
    -0.65
    olicy
    -0.64
    POSITIVE LOGITS
    naire
    1.71
    naires
    1.41
    aries
    1.16
    ary
    1.10
    ality
    1.08
    ettes
    1.08
    ysis
    1.07
    aires
    1.01
    omics
    0.97
    SHIP
    0.95
    Activations Density 0.058%

    No Known Activations