© 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. 0-RES-JB
    6. 14915
    Prev
    Next
    INDEX
    Explanations

    words related to the location "Tuscaloosa"

    oai_token-act-pair · gpt-3.5-turbo

    specific place names and references to locations

    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
     Express
    -0.83
     Boys
    -0.72
     Earthquake
    -0.70
    onite
    -0.68
     Hunter
    -0.66
    ICO
    -0.64
    lly
    -0.64
     Extreme
    -0.63
     Chaser
    -0.63
     Freeze
    -0.62
    POSITIVE LOGITS
    usc
    3.40
    pir
    2.44
    spir
    1.67
    piration
    1.40
     ped
    1.23
     Pik
    1.15
    ribut
    1.14
     spir
    1.12
     Spir
    1.12
    ÄŁ
    1.10
    Activations Density 0.044%

    No Known Activations