© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 2364
    Prev
    Next
    INDEX
    Explanations

    the word "Nam" followed by a number ranging from 9 to 10

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Namibia."

    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
     ske
    -0.66
     Fleet
    -0.65
    idge
    -0.64
    elli
    -0.64
    ockets
    -0.64
     ER
    -0.63
    iberal
    -0.62
    arrow
    -0.61
    akes
    -0.61
     CLIENT
    -0.60
    POSITIVE LOGITS
     Nam
    4.18
    nam
    1.38
     Niger
    1.25
     Berm
    1.23
     Zam
    1.19
     Tong
    1.19
     Dum
    1.17
     Chun
    1.13
     Nguyen
    1.13
     Lum
    1.11
    Activations Density 0.020%

    No Known Activations