© 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. 11-RES-JB
    11. 13744
    Prev
    Next
    INDEX
    Explanations

    words related to cyclones or cycling

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bicycles and cycling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    FORE
    -0.75
     Donetsk
    -0.62
     Bris
    -0.62
     Cheong
    -0.60
     Bots
    -0.60
     aside
    -0.59
     implanted
    -0.58
     peg
    -0.57
     tags
    -0.56
     Zucker
    -0.56
    POSITIVE LOGITS
    ical
    1.46
    icals
    1.25
    omatic
    1.20
    onic
    1.19
    ic
    1.16
    icism
    1.15
    ones
    1.12
    ically
    1.11
    oped
    1.07
    orama
    1.06
    Activations Density 0.056%

    No Known Activations