© 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. 4024
    Prev
    Next
    INDEX
    Explanations

    keywords related to the location "Panama."

    oai_token-act-pair · gpt-3.5-turbo

    references to Panama

    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
    ¢
    -0.70
    LY
    -0.69
    ergy
    -0.69
     ADC
    -0.69
     Lore
    -0.68
    ––
    -0.67
    ocations
    -0.63
    cknow
    -0.63
    urther
    -0.62
    ikes
    -0.62
    POSITIVE LOGITS
     Panama
    3.59
     Pirates
    1.44
    Pan
    1.41
     PAN
    1.03
     Pan
    1.01
     Panic
    1.00
     Bermuda
    0.99
     fal
    0.98
     Chong
    0.93
     Saras
    0.92
    Activations Density 0.021%

    No Known Activations