© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17263
    Prev
    Next
    INDEX
    Explanations

    mentions of political events and figures

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to political events and offenses

    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
    Weiss
    -0.87
    Cub
    -0.87
     Sounders
    -0.84
     Walt
    -0.81
     Weiss
    -0.80
     Becky
    -0.78
    Winter
    -0.77
    lando
    -0.76
     Myr
    -0.75
     [...]
    -0.73
    POSITIVE LOGITS
     Delhi
    1.90
     Maharashtra
    1.88
     Gujarat
    1.87
     Kerala
    1.82
     Rs
    1.81
     Bihar
    1.79
     lakh
    1.78
     Mumbai
    1.76
     Hindi
    1.76
    India
    1.74
    Activations Density 2.687%

    No Known Activations