© 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. 12703
    Prev
    Next
    INDEX
    Explanations

    words related to various activities and conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geological and biological concepts

    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
    NESS
    -0.60
     betrayal
    -0.60
     motto
    -0.57
    HOME
    -0.57
     Sutherland
    -0.54
     ethics
    -0.52
    nings
    -0.52
     fandom
    -0.52
     frustrations
    -0.52
     confessions
    -0.52
    POSITIVE LOGITS
    ivated
    1.31
    ificantly
    1.18
    itored
    1.12
    ilated
    1.11
    urated
    1.11
    iably
    1.11
    umbered
    1.10
    ivable
    1.10
    ibly
    1.09
    ographically
    1.09
    Activations Density 0.324%

    No Known Activations