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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 18728
    Prev
    Next
    INDEX
    Explanations

    terms related to legal or administrative procedures

    oai_token-act-pair · gpt-3.5-turbo

    strong statements about consequences or significant details regarding a topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Others
    -0.77
     Others
    -0.61
    ibliography
    -0.60
    obbies
    -0.56
     colourful
    -0.55
    Recently
    -0.55
    Topics
    -0.55
     Voc
    -0.54
    Sometimes
    -0.54
     Sometimes
    -0.53
    POSITIVE LOGITS
     ONLY
    0.82
     negate
    0.74
     preclude
    0.67
     NOT
    0.67
     guarantee
    0.66
     unless
    0.64
     preventing
    0.64
     guaranteeing
    0.63
    clusively
    0.63
     prevents
    0.62
    Activations Density 1.088%

    No Known Activations