© 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. 9-RES-JB
    11. 4147
    Prev
    Next
    INDEX
    Explanations

    dates

    oai_token-act-pair · gpt-3.5-turbo

    references to sports events and associated outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aminer
    -0.85
     continuum
    -0.73
    Translation
    -0.73
     memos
    -0.72
    soType
    -0.72
    FBI
    -0.71
    catentry
    -0.71
    forums
    -0.71
    Rate
    -0.70
    Demand
    -0.68
    POSITIVE LOGITS
     undefeated
    1.23
     defeated
    1.22
     unbeaten
    1.18
     defeating
    1.16
     defeat
    1.13
     victorious
    1.08
     victory
    1.07
     defeats
    1.07
     rematch
    1.06
     victories
    1.05
    Activations Density 0.527%

    No Known Activations