© 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. 3-RES-JB
    11. 7188
    Prev
    Next
    INDEX
    Explanations

    references to locations, especially through state abbreviations like "TX" and "UT"

    oai_token-act-pair · gpt-3.5-turbo

    references to locations, specifically in Texas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.98
    croft
    -0.78
     Alban
    -0.67
     Sunder
    -0.67
    antly
    -0.64
    stall
    -0.63
    shown
    -0.63
    leck
    -0.63
    cases
    -0.63
     Murdoch
    -0.62
    POSITIVE LOGITS
    TX
    1.08
     TX
    0.92
    ouble
    0.84
    NJ
    0.82
    VA
    0.79
    NY
    0.79
    HER
    0.78
    LV
    0.76
    LM
    0.76
    IED
    0.75
    Activations Density 0.010%

    No Known Activations