© 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. 11-RES-JB
    11. 1010
    Prev
    Next
    INDEX
    Explanations

    mentions of police actions such as detaining or arresting individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of arrests and detentions

    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
    taboola
    -0.93
    Interstitial
    -0.74
    opian
    -0.73
    wcsstore
    -0.70
    ãĤ¡
    -0.70
    HUD
    -0.70
    è£ħ
    -0.70
    ãĤ´ãĥ³
    -0.69
    POST
    -0.68
    mil
    -0.66
    POSITIVE LOGITS
     dozens
    0.94
     seven
    0.93
     five
    0.91
     nine
    0.91
     Imran
    0.90
     four
    0.89
     three
    0.89
     him
    0.89
     seventeen
    0.88
     eight
    0.88
    Activations Density 0.102%

    No Known Activations