© 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. 10317
    Prev
    Next
    INDEX
    Explanations

    the name "Jeff" with a high level of activation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Jeff"

    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
     womb
    -0.79
    xual
    -0.74
    velt
    -0.67
    ktop
    -0.63
    ãĥ´
    -0.62
    pmwiki
    -0.62
     Parenthood
    -0.61
     traged
    -0.61
    ãĥķãĤ©
    -0.61
     IMAGES
    -0.61
    POSITIVE LOGITS
    reys
    1.44
    ery
    1.33
    eries
    1.30
    rey
    1.29
    erey
    1.24
    erson
    1.18
     Bezos
    1.16
    ress
    1.02
    ries
    0.99
    isher
    0.96
    Activations Density 0.033%

    No Known Activations