© 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. 22610
    Prev
    Next
    INDEX
    Explanations

    references to the geographical location of Puerto Rico

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Puerto Rico and its context

    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
    abb
    -0.70
    Bre
    -0.68
    ings
    -0.67
    med
    -0.66
    Bir
    -0.65
     bir
    -0.64
    det
    -0.62
     sed
    -0.62
    augh
    -0.61
    att
    -0.60
    POSITIVE LOGITS
     Rico
    4.12
     Rican
    2.42
     Rica
    2.10
     Ric
    1.46
     Ricardo
    1.34
     Puerto
    1.20
     Janeiro
    1.12
     Scotia
    1.09
     Leone
    1.08
     Samoa
    1.08
    Activations Density 0.019%

    No Known Activations