© 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. 24282
    Prev
    Next
    INDEX
    Explanations

    the presence of end-of-text markers

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    programming-related terms, including code snippets and function names

    oai_token-act-pair · gpt-3.5-turbo
    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
     Grind
    -0.71
    chuk
    -0.62
     Coke
    -0.59
     hub
    -0.57
     Costco
    -0.57
     Barbar
    -0.56
     Horizon
    -0.54
    inness
    -0.54
     shenan
    -0.53
     blat
    -0.53
    POSITIVE LOGITS
     :=
    0.76
    channelAvailability
    0.75
     encoding
    0.70
    =-
    0.65
    initialized
    0.63
    soType
    0.63
    ãĥĺãĥ©
    0.62
    Reviewed
    0.62
     ):
    0.62
    _
    0.61
    Activations Density 0.188%

    No Known Activations