© 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. 9-RES-JB
    11. 5304
    Prev
    Next
    INDEX
    Explanations

    keywords related to transportation routes and destinations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating origins and destinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hairs
    -0.75
    edi
    -0.73
    Pattern
    -0.71
    HTML
    -0.70
    natureconservancy
    -0.68
    Changes
    -0.67
    archs
    -0.67
     inconsist
    -0.67
     suscept
    -0.67
    attribute
    -0.67
    POSITIVE LOGITS
     destinations
    1.13
     downtown
    1.12
     Calais
    1.08
     Kuala
    1.03
     Gat
    1.02
     Anchorage
    1.01
     Bangkok
    1.00
     Downtown
    1.00
     Junction
    0.99
     Istanbul
    0.99
    Activations Density 0.257%

    No Known Activations