© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2294
    Prev
    Next
    INDEX
    Explanations

    words related to emaciation or extreme thinness

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    words related to emotional or physical states of being

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     contextual
    -0.65
     webcam
    -0.61
     curated
    -0.58
     intentional
    -0.58
     Myst
    -0.56
     unmanned
    -0.55
     Eliot
    -0.54
     Tow
    -0.54
    åŃ
    -0.54
     Maher
    -0.54
    POSITIVE LOGITS
    inently
    1.43
    blems
    1.32
    perors
    1.27
    pathic
    1.27
    igration
    1.25
    inence
    1.25
    igrants
    1.19
    ulsion
    1.18
    igrated
    1.17
    ulated
    1.17
    Activations Density 0.009%

    No Known Activations