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. 9-RES-JB
    6. 5111
    Prev
    Next
    INDEX
    Explanations

    references to the location and sports team "Oklahoma City Thunder."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     istg
    -0.75
    ching
    -0.73
    ches
    -0.73
    brid
    -0.71
    âĸ¬
    -0.71
     Uriel
    -0.69
     Britann
    -0.68
    ########
    -0.66
    bred
    -0.66
    âĸ¬âĸ¬
    -0.65
    POSITIVE LOGITS
     City
    1.13
    lahoma
    1.03
    essee
    0.90
     Soon
    0.88
     Springs
    0.85
    oms
    0.83
    oya
    0.81
    onom
    0.79
    okin
    0.77
     Haram
    0.76
    Activations Density 0.037%

    No Known Activations