© 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. 12-RES-JB
    11. 2743
    Prev
    Next
    INDEX
    Explanations

    recommendations or instructions related to technology and productivity

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to cautions and recommendations for safe practices

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    oubted
    -0.63
     pione
    -0.62
    success
    -0.59
    icion
    -0.58
     teasp
    -0.58
    eret
    -0.57
     practition
    -0.57
    itivity
    -0.56
     Lovely
    -0.56
    ailability
    -0.55
    POSITIVE LOGITS
     unless
    1.78
    unless
    1.47
     nor
    1.43
     anymore
    1.36
     except
    1.23
     whatsoever
    1.17
     lest
    1.11
     until
    1.10
     EVER
    1.04
     Unless
    1.03
    Activations Density 0.536%

    No Known Activations