© 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. 10-RES-JB
    11. 5901
    Prev
    Next
    INDEX
    Explanations

    numerical values within a specific range

    oai_token-act-pair · gpt-3.5-turbo

    numbers and alphanumeric characters in a structured format

    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
     bloodstream
    -0.68
     GSL
    -0.68
     giveaways
    -0.62
     corridors
    -0.61
     SEC
    -0.60
     DEC
    -0.59
     EVER
    -0.58
     sorts
    -0.57
     CBO
    -0.56
     COM
    -0.56
    POSITIVE LOGITS
    ãĤ´ãĥ³
    0.95
    yu
    0.93
    ulhu
    0.89
    uclear
    0.85
    idia
    0.84
    é¾įåĸļ士
    0.83
    DragonMagazine
    0.81
    bh
    0.81
    upe
    0.81
    uid
    0.80
    Activations Density 0.239%

    No Known Activations