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. 13828
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations, specifically focusing on Queensland

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographic locations, specifically Queensland and Brisbane

    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
    abet
    -0.87
    udder
    -0.79
    ãĤ·ãĥ£
    -0.76
    igmat
    -0.76
    tered
    -0.72
    omsky
    -0.72
    coni
    -0.71
    ischer
    -0.71
    ocratic
    -0.70
    imov
    -0.69
    POSITIVE LOGITS
    ers
    1.01
     Queensland
    0.81
    shire
    0.79
     Papers
    0.73
     Gazette
    0.73
    ular
    0.70
    erness
    0.70
    emouth
    0.70
    ysis
    0.69
    interstitial
    0.68
    Activations Density 0.010%

    No Known Activations