© 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. 9-RES-JB
    11. 24319
    Prev
    Next
    INDEX
    Explanations

    instances of conversations or dialogues

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and"

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    uty
    -0.76
    itness
    -0.75
    Enlarge
    -0.74
    UC
    -0.70
    usk
    -0.69
    anmar
    -0.68
    DragonMagazine
    -0.68
    responsible
    -0.68
    odcast
    -0.67
    UAL
    -0.67
    POSITIVE LOGITS
     blah
    1.24
     stuff
    1.02
     forgot
    1.00
     nobody
    0.99
     thats
    0.99
     then
    0.97
     sucks
    0.93
     shit
    0.91
     didnt
    0.88
     couldn
    0.88
    Activations Density 0.281%

    No Known Activations