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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 10304
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations, especially in Hawaii

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and institutions in Hawaii

    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
     Petr
    -1.09
     Stafford
    -1.00
     Lanc
    -0.98
     Pistons
    -0.96
     Stras
    -0.96
     Notting
    -0.94
     Preston
    -0.85
    Detroit
    -0.85
    wagen
    -0.85
     ITV
    -0.84
    POSITIVE LOGITS
     Hawai
    2.65
     Honolulu
    2.39
     Hawaiian
    2.28
     Hawaii
    2.22
    Haw
    2.04
     Kau
    1.81
     Mau
    1.75
    olulu
    1.74
    Tai
    1.58
     Taiwanese
    1.56
    Activations Density 0.194%

    No Known Activations