Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 10979
    Prev
    Next
    INDEX
    Explanations

    names of countries related to South America

    oai_token-act-pair · gpt-3.5-turbo

    references to locations, particularly in relation to Peru

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.92
    tal
    -0.82
    ERAL
    -0.81
    ////////////////
    -0.78
    bler
    -0.77
    ulation
    -0.76
    gregation
    -0.75
    roads
    -0.75
    INAL
    -0.74
    hog
    -0.74
    POSITIVE LOGITS
     Peru
    0.94
    uvian
    0.87
     Lima
    0.75
     gardening
    0.74
     Bolivia
    0.68
    cious
    0.68
    isphere
    0.68
     Paragu
    0.67
    vati
    0.65
    Ton
    0.65
    Activations Density 0.012%

    No Known Activations