© 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. 9-RES-JB
    11. 4112
    Prev
    Next
    INDEX
    Explanations

    medical terms or health-related concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health issues and safety concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ´
    -0.75
    icter
    -0.68
    bern
    -0.65
    ificant
    -0.63
    stract
    -0.63
    Reviewer
    -0.62
    æĸ¹
    -0.61
    aeper
    -0.60
    itialized
    -0.60
    afort
    -0.59
    POSITIVE LOGITS
     ("
    0.86
     ($
    0.85
     ('
    0.77
     (#
    0.73
     syndrome
    0.71
     and
    0.71
     aka
    0.70
    ®,
    0.69
    worms
    0.67
    arettes
    0.67
    Activations Density 0.610%

    No Known Activations