© 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. 8-RES-JB
    11. 13043
    Prev
    Next
    INDEX
    Explanations

    diminutive phrases or expressions containing "lim"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "limousine."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ALK
    -0.75
     Aust
    -0.67
     pleas
    -0.61
    WR
    -0.61
     amd
    -0.61
     Wisconsin
    -0.58
    ãĤ¢ãĥ«
    -0.58
    gerald
    -0.58
    wright
    -0.57
    UP
    -0.57
    POSITIVE LOGITS
    elight
    1.38
    erick
    1.21
    itations
    1.18
    bered
    1.03
    iter
    1.02
    inished
    0.99
    itating
    0.99
    bers
    0.98
    psons
    0.97
    itation
    0.95
    Activations Density 0.028%

    No Known Activations