© 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. 24292
    Prev
    Next
    INDEX
    Explanations

    organizations or institutions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks at the end of sentences

    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
     sleeper
    -0.69
     opio
    -0.69
     wardrobe
    -0.68
     endeav
    -0.66
     scrimmage
    -0.64
     eternity
    -0.62
     royalty
    -0.61
     ponies
    -0.60
     mistress
    -0.59
     vag
    -0.59
    POSITIVE LOGITS
     He
    1.07
     Previously
    1.03
     Others
    1.00
     His
    0.98
     Speaking
    0.98
     Asked
    0.96
     Having
    0.95
     Though
    0.94
     Typically
    0.94
     Many
    0.94
    Activations Density 0.307%

    No Known Activations