© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 13176
    Prev
    Next
    INDEX
    Explanations

    names or terms related to "Ga" or "Georgia"

    oai_token-act-pair · gpt-3.5-turbo

    references to the state of Georgia

    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
    enance
    -0.90
    ty
    -0.80
    tenance
    -0.74
    sburgh
    -0.73
    neys
    -0.72
    journal
    -0.71
    payer
    -0.70
    topic
    -0.69
    irements
    -0.68
    bucks
    -0.68
    POSITIVE LOGITS
    Ga
    1.44
     Ga
    1.25
    ither
    0.98
    pless
    0.92
    vernment
    0.91
    keye
    0.85
     exha
    0.83
    etz
    0.82
    illard
    0.81
    ussian
    0.79
    Activations Density 0.005%

    No Known Activations