© 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. 8-RES-JB
    11. 22532
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Kenya and its people

    oai_token-act-pair · gpt-3.5-turbo

    the mention of the name "Kenya."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Catalog
    -0.63
     Coil
    -0.63
    >>\
    -0.59
     RESP
    -0.58
     prov
    -0.56
    ITIES
    -0.55
    swick
    -0.55
    DERR
    -0.55
     Odyssey
    -0.55
     Merchants
    -0.55
    POSITIVE LOGITS
    enne
    0.99
    ielding
    0.96
    oga
    0.96
    ield
    0.93
    anka
    0.92
    vind
    0.87
    ank
    0.87
    onder
    0.85
    aku
    0.85
    nda
    0.84
    Activations Density 0.064%

    No Known Activations