© 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. 6-RES-JB
    11. 9347
    Prev
    Next
    INDEX
    Explanations

    words related to specific categories or types

    oai_token-act-pair · gpt-3.5-turbo

    references to specific categories or classifications of things

    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
    perse
    -0.62
    Tro
    -0.62
     kidding
    -0.61
     Lia
    -0.60
    ĸļ
    -0.59
    GGGG
    -0.59
    BuyableInstoreAndOnline
    -0.59
    cknowled
    -0.59
    shed
    -0.57
     unden
    -0.56
    POSITIVE LOGITS
     thresholds
    0.76
    Ore
    0.73
     threshold
    0.69
     alters
    0.65
    Keefe
    0.63
    ASON
    0.63
     subset
    0.63
    olson
    0.62
    itions
    0.61
    ittees
    0.61
    Activations Density 0.143%

    No Known Activations