© 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. 8-RES-JB
    11. 1215
    Prev
    Next
    INDEX
    Explanations

    words related to a specific person's name

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the syllable "ab" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     remed
    -0.58
     failing
    -0.58
     LIA
    -0.57
     Marvin
    -0.57
     Bened
    -0.57
     Carlson
    -0.56
     bailed
    -0.56
     mascul
    -0.56
     Christensen
    -0.55
     Patriot
    -0.54
    POSITIVE LOGITS
    augh
    0.96
    oard
    0.93
    udd
    0.87
    urger
    0.87
    acteria
    0.86
    ilk
    0.86
    uku
    0.86
    ecause
    0.84
    estic
    0.80
    odies
    0.80
    Activations Density 0.077%

    No Known Activations