© 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. 3689
    Prev
    Next
    INDEX
    Explanations

    names of political figures and locations

    oai_token-act-pair · gpt-3.5-turbo

    political names and titles related to leadership

    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
    Egypt
    -1.16
    Tesla
    -1.11
     Memphis
    -1.04
    NBA
    -1.03
     Tesla
    -1.00
     Egyptians
    -1.00
     Bezos
    -1.00
     Grizzlies
    -1.00
     Mubarak
    -0.99
     Egyptian
    -0.95
    POSITIVE LOGITS
     Irish
    1.93
    Irish
    1.93
     Dublin
    1.92
    Ireland
    1.86
     Ireland
    1.81
     Cork
    1.76
     Ulster
    1.69
     Sinn
    1.68
     Gael
    1.61
     TDs
    1.59
    Activations Density 0.412%

    No Known Activations