© 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. 4-RES-JB
    11. 20910
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical entities, specifically focusing on Bulgaria

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Bulgaria and its regional context

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

    No Comments

    Negative Logits
    lich
    -0.86
    bow
    -0.82
    eering
    -0.78
    oller
    -0.77
    clair
    -0.75
    afort
    -0.74
    ebus
    -0.73
     Doodle
    -0.73
    awaru
    -0.73
    eer
    -0.73
    POSITIVE LOGITS
    halla
    0.93
    é¾
    0.91
    wana
    0.86
     volumes
    0.73
    aneers
    0.71
    OAD
    0.69
    anca
    0.68
    éļ
    0.68
     Incarn
    0.66
    çĦ
    0.66
    Activations Density 0.040%

    No Known Activations