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. 4683
    Prev
    Next
    INDEX
    Explanations

    mentions of a sports team named the Orioles

    oai_token-act-pair · gpt-3.5-turbo

    references to the Baltimore Orioles baseball team

    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
    utterstock
    -0.86
    anwhile
    -0.81
    itably
    -0.74
    uters
    -0.72
    eting
    -0.71
    pter
    -0.70
    quickShipAvailable
    -0.68
    eger
    -0.66
    ppe
    -0.65
    trak
    -0.64
    POSITIVE LOGITS
     Orioles
    1.29
     outfielder
    0.86
    zag
    0.77
     Ori
    0.77
     Baseball
    0.76
     pitchers
    0.69
     Odyssey
    0.69
     Ravens
    0.67
    yssey
    0.65
     Tornado
    0.65
    Activations Density 0.008%

    No Known Activations