© 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. 6-RES-JB
    11. 10345
    Prev
    Next
    INDEX
    Explanations

    physical attributes or medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with healthcare, law enforcement, and societal norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )=(
    -0.55
    istrate
    -0.52
    shapeshifter
    -0.49
    etimes
    -0.49
    minist
    -0.49
    earable
    -0.48
    addon
    -0.48
     Canaver
    -0.47
    enum
    -0.46
     archived
    -0.45
    POSITIVE LOGITS
     or
    0.81
     etc
    0.75
    /.
    0.60
     and
    0.59
    /
    0.56
     &
    0.52
    _.
    0.52
     et
    0.52
    ®,
    0.51
    *.
    0.50
    Activations Density 1.159%

    No Known Activations