© 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. 13344
    Prev
    Next
    INDEX
    Explanations

    words related to reclaiming or recovering something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "rec" in various forms related to records or actions of reconsideration

    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
    MENT
    -0.70
    MENTS
    -0.64
    nuts
    -0.64
    hole
    -0.64
     FDR
    -0.63
    holes
    -0.62
    externalActionCode
    -0.60
    tery
    -0.60
    buster
    -0.60
     Masters
    -0.60
    POSITIVE LOGITS
    ategor
    1.26
    ourses
    1.13
    urrence
    1.10
    usal
    1.05
    ieved
    1.03
    ieving
    1.03
    irc
    1.02
    ursion
    1.00
    iever
    1.00
    onduct
    0.99
    Activations Density 0.016%

    No Known Activations