© 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. 2732
    Prev
    Next
    INDEX
    Explanations

    personal pronouns like "he" or "they"

    oai_token-act-pair · gpt-3.5-turbo

    references to male individuals in a context of actions or descriptions

    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
     fuse
    -0.70
     brill
    -0.69
     Pegasus
    -0.69
     Armageddon
    -0.68
     Forth
    -0.68
     Hercules
    -0.66
     ripple
    -0.66
     Newark
    -0.65
     JFK
    -0.65
     Keynes
    -0.64
    POSITIVE LOGITS
    âĢ
    2.36
     âĢ
    1.80
    âĶ
    1.49
    âľ
    1.47
    ãĢ
    1.42
    â
    1.38
    âĢł
    1.38
    âĸł
    1.35
    ï
    1.33
    ¨
    1.32
    Activations Density 0.645%

    No Known Activations