© 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. 920
    Prev
    Next
    INDEX
    Explanations

    information related to concepts in technology and politics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to systems, structures, and societal concepts

    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
    ibur
    -0.74
    ãĥĦ
    -0.63
    cause
    -0.63
    apult
    -0.63
    kefeller
    -0.62
    anwhile
    -0.61
    aciously
    -0.61
    Alert
    -0.60
    boss
    -0.58
    untarily
    -0.58
    POSITIVE LOGITS
     there
    0.95
    ,
    0.81
     these
    0.78
     it
    0.72
     (),
    0.71
     alike
    0.68
    ,...
    0.68
     people
    0.66
     individuals
    0.66
     ,
    0.66
    Activations Density 0.363%

    No Known Activations