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. 1-RES-JB
    6. 12081
    Prev
    Next
    INDEX
    Explanations

    mentions of the city "Sao Paulo"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of specific names and locations, particularly in relation to São Paulo

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NESS
    -1.01
    âĸ¬âĸ¬
    -0.82
    RAY
    -0.82
     Grape
    -0.76
    POSE
    -0.75
    WARE
    -0.74
    IBLE
    -0.74
    LEY
    -0.73
     Garland
    -0.73
     Kessler
    -0.72
    POSITIVE LOGITS
     Sao
    1.15
    ulative
    0.84
    isma
    0.81
    obiles
    0.79
    uters
    0.76
    isSpecialOrderable
    0.74
    obic
    0.74
    ulus
    0.73
     Corinthians
    0.73
    terior
    0.73
    Activations Density 0.024%

    No Known Activations