© 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. 10-RES-JB
    11. 7796
    Prev
    Next
    INDEX
    Explanations

    trigger words that prompt action related to printing or distribution

    oai_token-act-pair · gpt-3.5-turbo

    references to the action of printing or options related to printing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hov
    -0.76
    olate
    -0.63
    arios
    -0.62
    esson
    -0.60
     towed
    -0.60
     Oaks
    -0.60
     smoot
    -0.58
    vre
    -0.58
    opoulos
    -0.57
    uster
    -0.57
    POSITIVE LOGITS
    able
    1.09
    ables
    0.87
    ername
    0.82
    out
    0.80
    outs
    0.78
     editions
    0.75
    Writer
    0.73
    ability
    0.73
    casters
    0.72
     Friendly
    0.71
    Activations Density 0.019%

    No Known Activations