© 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. 3281
    Prev
    Next
    INDEX
    Explanations

    locations or events related to legal issues or law enforcement

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

    locations related to community services and places of interest

    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
    adders
    -0.90
    taboola
    -0.80
    ãĥīãĥ©
    -0.77
    awatts
    -0.75
     Plans
    -0.72
    keyes
    -0.72
     Acts
    -0.71
     Cosponsors
    -0.69
     Statements
    -0.69
     Parables
    -0.68
    POSITIVE LOGITS
     frequ
    1.21
     owned
    0.99
     staffed
    0.93
     called
    0.90
     nearby
    0.87
     restroom
    0.85
     near
    0.83
     stall
    0.83
     populated
    0.82
     brawl
    0.82
    Activations Density 0.306%

    No Known Activations