© 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. 12811
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical regions, particularly related to the Kurdistan area

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Kurdistan region and relevant political 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
    eric
    -0.83
    EMENT
    -0.78
    ebus
    -0.76
    boxes
    -0.76
    ysis
    -0.75
    ym
    -0.73
    ecast
    -0.72
    verson
    -0.71
    irement
    -0.70
    ered
    -0.69
    POSITIVE LOGITS
     Region
    1.00
     Haram
    0.95
    istani
    0.95
     Kurdistan
    0.88
     Regional
    0.80
     Pradesh
    0.80
     Province
    0.79
     Municip
    0.79
    inational
    0.71
     Azerb
    0.70
    Activations Density 0.028%

    No Known Activations