© 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. 3-RES-JB
    11. 16161
    Prev
    Next
    INDEX
    Explanations

    phrases related to awards, achievements, and accolades

    oai_token-act-pair · gpt-3.5-turbo

    terms that describe critical social issues or underrepresented groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.64
    ãĥ¼ãĥĨ
    -0.58
     Leilan
    -0.56
    arettes
    -0.55
     Vaugh
    -0.55
     Azerb
    -0.55
     Moroc
    -0.54
    emale
    -0.54
    chuk
    -0.54
    ankind
    -0.53
    POSITIVE LOGITS
     matchup
    0.49
    ÂŃ
    0.48
    pit
    0.48
     pit
    0.48
     lineup
    0.47
     interpreter
    0.46
     image
    0.46
     package
    0.46
     largeDownload
    0.46
     Autob
    0.46
    Activations Density 1.679%

    No Known Activations