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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20138
    Prev
    Next
    INDEX
    Explanations

    locations or places, specifically cities and neighborhoods

    oai_token-act-pair · gpt-3.5-turbo

    specific city names or locations, particularly in California and Texas

    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
     mete
    -0.73
     peer
    -0.68
     Rebell
    -0.67
    DragonMagazine
    -0.67
     resume
    -0.64
    adder
    -0.63
    employed
    -0.62
     ransom
    -0.61
     sentence
    -0.60
    nown
    -0.60
    POSITIVE LOGITS
     Aires
    1.04
     Mesa
    1.03
     Alto
    1.01
     Janeiro
    1.01
     Angeles
    1.00
     Highlands
    0.98
     Ranch
    0.93
     Paso
    0.93
     Vista
    0.92
     Mirage
    0.91
    Activations Density 0.117%

    No Known Activations