© 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. 11370
    Prev
    Next
    INDEX
    Explanations

    mentions of countries or entities

    oai_token-act-pair · gpt-3.5-turbo

    the article "the" and references to the US or its government

    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
    herer
    -0.81
    Guest
    -0.81
    Cod
    -0.75
    !'
    -0.72
    ropolitan
    -0.71
    Scroll
    -0.71
    erella
    -0.71
    ipedia
    -0.69
    TPPStreamerBot
    -0.69
    arry
    -0.68
    POSITIVE LOGITS
     decision
    1.19
     situation
    1.09
     timing
    1.07
     reason
    1.04
     goal
    1.02
     idea
    1.01
     omission
    1.00
     intention
    1.00
     aim
    1.00
     lack
    1.00
    Activations Density 0.301%

    No Known Activations