© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RES-JB
    11. 5173
    Prev
    Next
    INDEX
    Explanations

    companies or organizations

    oai_token-act-pair · gpt-3.5-turbo
    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
     Curious
    -0.52
     Highland
    -0.51
     Crescent
    -0.50
    amaz
    -0.49
     Nickel
    -0.49
    Redd
    -0.49
    Spot
    -0.49
     Pict
    -0.48
     Fren
    -0.48
    âĸ
    -0.48
    POSITIVE LOGITS
     didnt
    1.14
     dont
    1.12
     cannot
    1.06
     ought
    1.04
     doesnt
    1.03
     SHOULD
    1.03
     wont
    1.02
     should
    0.95
     would
    0.95
     could
    0.93
    Activations Density 0.470%

    No Known Activations