© 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. 0-RES-JB
    11. 9630
    Prev
    Next
    INDEX
    Explanations

    references to documents or official documentation

    oai_token-act-pair · gpt-3.5-turbo

    references to documentation and academic work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plurality
    -0.70
     charm
    -0.67
    Ble
    -0.66
     Peach
    -0.65
     franchises
    -0.65
     Franch
    -0.64
    issance
    -0.63
     Lauder
    -0.63
     signific
    -0.63
     Appeal
    -0.63
    POSITIVE LOGITS
    doc
    3.72
    docs
    2.74
    doctoral
    2.00
     doc
    1.88
    Files
    1.73
    Doc
    1.57
    DOC
    1.51
    document
    1.44
    Document
    1.44
    files
    1.28
    Activations Density 0.022%

    No Known Activations