© 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. 13430
    Prev
    Next
    INDEX
    Explanations

    mentions of studies, research, analysis, or recommendations from previous instances

    oai_token-act-pair · gpt-3.5-turbo

    references to prior studies or research findings

    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
     scissors
    -0.67
    ogie
    -0.61
    stairs
    -0.60
    aleigh
    -0.60
     afterward
    -0.58
    etition
    -0.58
     everyday
    -0.57
     conscience
    -0.56
    ueller
    -0.56
     tomorrow
    -0.56
    POSITIVE LOGITS
     relied
    0.99
     tended
    0.90
     lacked
    0.84
    ptions
    0.76
     dealt
    0.75
     underestimated
    0.74
     failed
    0.72
     consisted
    0.71
    ceptions
    0.71
    uggest
    0.71
    Activations Density 0.256%

    No Known Activations