© 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. 12-RES-JB
    11. 2285
    Prev
    Next
    INDEX
    Explanations

    statements of opportunities, uncertainties, and turning points in current events

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    prepositions used in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.87
    geist
    -0.86
    zek
    -0.85
    =-=-=-=-
    -0.83
    mens
    -0.83
    culated
    -0.82
    arse
    -0.81
    minus
    -0.81
    heit
    -0.79
     ILCS
    -0.78
    POSITIVE LOGITS
     succeeding
    1.30
     encountering
    1.26
     catching
    1.25
     surviving
    1.21
     winning
    1.18
     becoming
    1.16
     reaching
    1.16
     obtaining
    1.15
     finding
    1.15
     retaining
    1.15
    Activations Density 0.161%

    No Known Activations