Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 23690
    Prev
    Next
    INDEX
    Explanations

    references to the city of Atlanta and related entities, such as events, locations, government officials, and media outlets

    oai_token-act-pair · gpt-3.5-turbo

    geographical references and specific locations related to Atlanta, Georgia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Xie
    -1.04
     LR
    -1.00
     scient
    -1.00
     Huss
    -0.94
     Droid
    -0.92
     Tibetan
    -0.92
     Scient
    -0.89
     Tibet
    -0.88
     pope
    -0.87
     pap
    -0.85
    POSITIVE LOGITS
    Atlanta
    2.25
     Atlanta
    2.25
     Georgia
    2.21
    Georgia
    2.15
     Braves
    1.84
     Fulton
    1.82
     Georgian
    1.82
     Cobb
    1.71
     Falcons
    1.71
     GA
    1.63
    Activations Density 0.319%

    No Known Activations