© 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. 4-RES-JB
    11. 10044
    Prev
    Next
    INDEX
    Explanations

    mathematical or coding expressions involving variables and functions

    oai_token-act-pair · gpt-3.5-turbo

    elements related to programming syntax and functions

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

    No Comments

    Negative Logits
     lobb
    -0.64
     agre
    -0.62
     Volunte
    -0.60
     Cosponsors
    -0.60
     Client
    -0.59
     acron
    -0.59
     Practices
    -0.59
     Citation
    -0.59
    wcs
    -0.59
    accompan
    -0.58
    POSITIVE LOGITS
    âĪĴ
    0.83
    \)
    0.77
    uple
    0.77
    Ïī
    0.73
     ).
    0.73
    )=(
    0.72
     nucleus
    0.72
     )]
    0.70
     ),
    0.70
     âĪĴ
    0.69
    Activations Density 0.152%

    No Known Activations