© 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. 9-RES-JB
    11. 10405
    Prev
    Next
    INDEX
    Explanations

    references to governmental bodies and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to authoritative entities and figures in discussions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    %%%%
    -0.65
    orts
    -0.59
    -+
    -0.59
    quickShipAvailable
    -0.58
     prev
    -0.58
    atre
    -0.57
     Theft
    -0.57
     Misc
    -0.55
     Spend
    -0.52
    cffffcc
    -0.52
    POSITIVE LOGITS
     via
    0.86
     orally
    0.81
     detriment
    0.72
    è¦ļéĨĴ
    0.70
    selves
    0.66
     electronically
    0.66
     beforehand
    0.66
     coffers
    0.65
    çīĪ
    0.64
     satisfaction
    0.63
    Activations Density 0.543%

    No Known Activations