© 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. 0-RES-JB
    11. 2701
    Prev
    Next
    INDEX
    Explanations

    references to the term "usa"

    oai_token-act-pair · gpt-3.5-turbo

    references to the United States and individuals associated with significant events or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sins
    -0.73
     Gentleman
    -0.72
     Rouge
    -0.71
     Pog
    -0.70
     Remastered
    -0.70
     Spect
    -0.69
    appings
    -0.68
     Falcons
    -0.67
     Brook
    -0.67
     Masquerade
    -0.66
    POSITIVE LOGITS
    usa
    2.98
    ector
    1.45
    uler
    1.32
    asta
    1.29
    ega
    1.28
     Osama
    1.19
    arta
    1.17
    ulla
    1.15
     Marina
    1.03
    ula
    1.02
    Activations Density 0.049%

    No Known Activations