© 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. 10252
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by a noun phrase indicating a location or state

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "in" followed by varying contexts or situations

    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
    Kids
    -0.58
     aside
    -0.57
    Desc
    -0.55
     charism
    -0.54
    CRIPTION
    -0.54
     alloc
    -0.53
    ById
    -0.53
     merits
    -0.53
     Doodle
    -0.53
     brethren
    -0.53
    POSITIVE LOGITS
    ching
    1.21
    escap
    1.03
    strument
    0.99
    humane
    0.99
    offensive
    0.96
    bred
    0.95
    patient
    0.94
    authent
    0.94
    animate
    0.94
     bed
    0.94
    Activations Density 0.151%

    No Known Activations