© 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. 1-RES-JB
    6. 21327
    Prev
    Next
    INDEX
    Explanations

    mentions of countries or regions

    oai_token-act-pair · gpt-3.5-turbo

    references to Southeast Asia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ierrez
    -0.67
     unnatural
    -0.67
    iants
    -0.66
    raviolet
    -0.64
    keyes
    -0.63
     setting
    -0.63
     resting
    -0.62
    ocado
    -0.62
    starter
    -0.60
     imposing
    -0.60
    POSITIVE LOGITS
    SE
    1.38
    ASON
    1.14
    ARCH
    1.12
    VEN
    1.10
    VER
    1.03
    VERS
    1.03
    WHERE
    0.96
    ATTLE
    0.95
    ldom
    0.94
    SEA
    0.91
    Activations Density 0.007%

    No Known Activations