© 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. 1-RES-JB
    11. 6592
    Prev
    Next
    INDEX
    Explanations

    words related to medical implants or procedures

    oai_token-act-pair · gpt-3.5-turbo

    the letter "w"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     susceptibility
    -0.82
    milo
    -0.81
     nomine
    -0.79
    EStream
    -0.77
     sensitivity
    -0.77
     mosqu
    -0.76
     penetrating
    -0.73
     paraly
    -0.72
     flush
    -0.71
     unpre
    -0.71
    POSITIVE LOGITS
    itness
    1.30
    atts
    1.27
    elcome
    1.23
    ashington
    1.19
    restling
    1.15
    arsh
    1.14
    w
    1.09
    ulf
    1.08
    edge
    1.07
    izard
    1.06
    Activations Density 0.016%

    No Known Activations