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. 4-RES-JB
    6. 3124
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, specifically related to the state of Uttar Pradesh

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations, particularly in India

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

    No Comments

    Negative Logits
    ³³³³³³³³³³³³³³³³
    -0.71
    SPONSORED
    -0.69
     responsive
    -0.66
    netflix
    -0.65
     deaf
    -0.64
     conditioning
    -0.64
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.64
    INESS
    -0.64
     Hurricanes
    -0.64
     Whitman
    -0.62
    POSITIVE LOGITS
     Pradesh
    1.48
    prising
    0.96
    arak
    0.96
    seys
    0.94
    ril
    0.94
     Haram
    0.93
    pling
    0.93
    arat
    0.89
    kee
    0.89
    anch
    0.88
    Activations Density 0.010%

    No Known Activations