© 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. 0-RES-JB
    11. 15418
    Prev
    Next
    INDEX
    Explanations

    references to physical or psychological symptoms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to symptoms and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urry
    -0.80
     Guns
    -0.78
     drafts
    -0.77
    unks
    -0.70
     Buster
    -0.68
     junk
    -0.68
     Junk
    -0.68
    eway
    -0.67
    defense
    -0.67
    endish
    -0.66
    POSITIVE LOGITS
     sympt
    2.23
     endemic
    1.63
     symptom
    1.61
     McA
    1.51
     ante
    1.42
     indicative
    1.31
     emblem
    1.23
     hypocritical
    1.22
     hypoc
    1.14
     bol
    1.00
    Activations Density 0.072%

    No Known Activations