© 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. 3044
    Prev
    Next
    INDEX
    Explanations

    names or terms related to legal cases and events

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

    instances of the name "Swanson" or variations of the name in various contexts

    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
     clipboard
    -0.79
     flares
    -0.78
     unprepared
    -0.75
     understatement
    -0.73
     short
    -0.72
     flared
    -0.71
     mistaken
    -0.71
     timely
    -0.71
     misinformation
    -0.71
     hesitate
    -0.71
    POSITIVE LOGITS
    artz
    1.52
    inton
    1.37
    enson
    1.35
    isher
    1.35
    indle
    1.32
    ensen
    1.29
    imming
    1.28
    anton
    1.28
    amin
    1.27
    erd
    1.25
    Activations Density 0.010%

    No Known Activations