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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 16342
    Prev
    Next
    INDEX
    Explanations

    references to historical events and political entities, specifically related to the Balkans

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific geographic regions and their associated historical events

    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
     locality
    -0.69
    ikawa
    -0.66
     angels
    -0.66
    emi
    -0.65
    schild
    -0.65
    emale
    -0.64
     Fey
    -0.64
     pard
    -0.63
    awan
    -0.63
    kson
    -0.62
    POSITIVE LOGITS
    Bul
    2.93
    Nut
    1.29
     Bullet
    0.95
    Reviewed
    0.92
    Hung
    0.87
    Reviewer
    0.79
    Dig
    0.79
    ocal
    0.78
    Cele
    0.78
    Palest
    0.78
    Activations Density 0.005%

    No Known Activations