© 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. 7-RES-JB
    11. 2875
    Prev
    Next
    INDEX
    Explanations

    locations or events associated with specific state abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    geographic identifiers, specifically related to locations in North Carolina and New York

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bumper
    -0.78
    20439
    -0.70
    Accessory
    -0.69
     balcon
    -0.67
    Reloaded
    -0.67
     casualty
    -0.66
     plank
    -0.65
     sleeper
    -0.63
     shutter
    -0.63
     pause
    -0.60
    POSITIVE LOGITS
    union
    0.81
    isco
    0.80
    fecture
    0.78
    nesota
    0.76
    .,
    0.73
    adelphia
    0.71
     Lumpur
    0.69
    olulu
    0.68
     Tenn
    0.67
    onda
    0.67
    Activations Density 0.084%

    No Known Activations