© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 22659
    Prev
    Next
    INDEX
    Explanations

    words related to the country Bosnia

    oai_token-act-pair · gpt-3.5-turbo

    references to the Bosnian conflict and related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yrinth
    -0.78
     lockout
    -0.73
    uate
    -0.71
    orage
    -0.64
    uating
    -0.63
    ATA
    -0.63
     Capitals
    -0.62
    rained
    -0.60
     Immunity
    -0.60
    ICES
    -0.60
    POSITIVE LOGITS
    nian
    1.29
    etooth
    1.00
    meric
    0.99
    combe
    0.94
    hea
    0.93
    hett
    0.92
    grain
    0.90
    chet
    0.89
    colo
    0.89
    atell
    0.87
    Activations Density 0.020%

    No Known Activations