© 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. 11-RES-JB
    11. 6173
    Prev
    Next
    INDEX
    Explanations

    programming code snippets related to setting and adjusting values

    oai_token-act-pair · gpt-3.5-turbo

    code-related terms and structures pertaining to programming and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Plays
    -0.88
     Strongh
    -0.82
     Houses
    -0.80
     Contracts
    -0.80
    Fair
    -0.78
     Reps
    -0.77
     Sites
    -0.77
     Passage
    -0.77
     Settlement
    -0.77
    Stretch
    -0.77
    POSITIVE LOGITS
     car
    0.81
     mult
    0.80
     auto
    0.77
     nil
    0.76
     boolean
    0.76
     ind
    0.76
     num
    0.76
     non
    0.76
     const
    0.76
     default
    0.76
    Activations Density 0.298%

    No Known Activations