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

    Neuronpedia

    APICircuit 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. 3-RES-JB
    6. 11796
    Prev
    Next
    INDEX
    Explanations

    terms related to the city of Los Angeles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Los Angeles."

    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
    ebook
    -0.85
    BOOK
    -0.84
    oulos
    -0.79
     tremend
    -0.74
    ãĤ¡
    -0.73
    ourgeois
    -0.71
    ICLE
    -0.70
    schild
    -0.70
     miscarriage
    -0.70
    displayText
    -0.67
    POSITIVE LOGITS
     Angeles
    1.61
     Alam
    1.00
     Santos
    0.95
    ction
    0.91
     Lumpur
    0.87
    ites
    0.85
     Rey
    0.83
     Padres
    0.81
     ANGEL
    0.76
     Dos
    0.76
    Activations Density 0.011%

    No Known Activations