© 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. 3-RES-JB
    11. 24508
    Prev
    Next
    INDEX
    Explanations

    programming code and syntax

    oai_token-act-pair · gpt-3.5-turbo

    references to data structures or algorithmic terms in computational contexts

    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
     guiName
    -0.88
    etheless
    -0.80
    wcs
    -0.71
    [/
    -0.67
    ãĢIJ
    -0.63
     :=
    -0.61
    minist
    -0.60
    .<
    -0.54
    ________________________________
    -0.52
    ":[{"
    -0.52
    POSITIVE LOGITS
    !)
    1.54
    )
    1.53
    ?)
    1.51
    )."
    1.49
    âĢ¦)
    1.49
    )"
    1.48
    ),"
    1.44
    )-
    1.40
    )'
    1.39
    ).
    1.39
    Activations Density 1.342%

    No Known Activations