© 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. 3-RES-JB
    11. 10786
    Prev
    Next
    INDEX
    Explanations

    references to a specific place, likely an institution or museum

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Hall of Fame."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eleph
    -0.77
     Gork
    -0.71
    phrine
    -0.66
    ossibility
    -0.64
     oppos
    -0.64
    uyomi
    -0.62
    ften
    -0.61
    nces
    -0.61
    ropolitan
    -0.61
     Raf
    -0.60
    POSITIVE LOGITS
    iday
    1.41
    ibur
    1.16
    aday
    1.06
    oran
    1.05
    gren
    1.01
    Hall
    0.98
    igan
    0.96
    owed
    0.96
    ows
    0.95
    way
    0.93
    Activations Density 0.009%

    No Known Activations