© 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 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. 6-RES-JB
    11. 14703
    Prev
    Next
    INDEX
    Explanations

    names of medications

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to specific legal or regulatory terms and classifications

    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
     sid
    -0.65
     wast
    -0.64
     handic
    -0.64
     wrist
    -0.63
     RELE
    -0.63
     puzz
    -0.62
     ASC
    -0.60
     blind
    -0.60
     metast
    -0.60
     tight
    -0.59
    POSITIVE LOGITS
    arie
    0.92
    idation
    0.91
    gettable
    0.90
    idy
    0.89
    ote
    0.88
    ÃŃn
    0.88
    opa
    0.87
    fleet
    0.87
    acular
    0.87
    usk
    0.86
    Activations Density 0.260%

    No Known Activations