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. 8787
    Prev
    Next
    INDEX
    Explanations

    US state names

    oai_token-act-pair · gpt-3.5-turbo

    geographic names and locations, specifically related to the states and areas

    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
    idious
    -0.81
    aphael
    -0.79
    otation
    -0.74
    GER
    -0.72
    aeus
    -0.70
    byn
    -0.70
    MAT
    -0.68
    together
    -0.68
    ods
    -0.67
    sheet
    -0.67
    POSITIVE LOGITS
     County
    0.98
     Railroad
    0.89
    aukee
    0.87
     Highway
    0.86
     Heights
    0.86
     Chiefs
    0.86
     Oaks
    0.86
    sylvania
    0.85
     Parkway
    0.84
     Territories
    0.82
    Activations Density 0.103%

    No Known Activations