© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 14333
    Prev
    Next
    INDEX
    Explanations

    quantitative statements about frequencies or proportions

    oai_token-act-pair · gpt-3.5-turbo

    the word "only" and its variations, indicating exclusivity or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    insula
    -0.83
    ciation
    -0.72
    etc
    -0.72
    iller
    -0.70
    llah
    -0.65
    bender
    -0.64
    ahead
    -0.64
    ystem
    -0.64
    rise
    -0.63
    comb
    -0.63
    POSITIVE LOGITS
     marginally
    0.83
     kidding
    0.82
     ONE
    0.82
     fools
    0.80
     idiots
    0.68
     TWO
    0.68
     THEN
    0.67
     twelve
    0.67
     mildly
    0.67
     AFTER
    0.67
    Activations Density 0.056%

    No Known Activations