© 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. 1-RES-JB
    11. 10458
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or entity associated with the term "Tuzla."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    displayText
    -0.71
    dayName
    -0.70
     Presents
    -0.69
    states
    -0.69
    recomm
    -0.69
    OFF
    -0.69
     Cosponsors
    -0.67
    design
    -0.66
     Prediction
    -0.66
    sets
    -0.65
    POSITIVE LOGITS
    uthor
    0.97
    uder
    0.95
    la
    0.93
    izabeth
    0.90
    usk
    0.87
    isa
    0.87
    uren
    0.87
    ptin
    0.83
    ques
    0.82
     Mae
    0.80
    Activations Density 0.007%

    No Known Activations