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. 2-RES-JB
    6. 3761
    Prev
    Next
    INDEX
    Explanations

    words related to a specific geographical location, specifically "Leicester."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the football club Leicester City

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icts
    -0.83
    sch
    -0.82
    psc
    -0.82
    Reviewer
    -0.79
    76561
    -0.79
    swing
    -0.72
    vg
    -0.72
    lopp
    -0.70
    mit
    -0.69
    anol
    -0.69
    POSITIVE LOGITS
    icester
    1.03
     Leicester
    0.89
    ©¶æ¥µ
    0.75
    shire
    0.73
    ury
    0.70
     Square
    0.69
     Yard
    0.69
     Tigers
    0.69
     Township
    0.68
    wich
    0.68
    Activations Density 0.009%

    No Known Activations