Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 293
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the city of Baltimore

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Baltimore" and its related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -1.05
    uador
    -0.89
    mble
    -0.85
    utterstock
    -0.80
    yss
    -0.77
    pter
    -0.76
    aeda
    -0.76
    wagen
    -0.75
    aterasu
    -0.74
    rencies
    -0.74
    POSITIVE LOGITS
     Orioles
    1.20
     Ravens
    1.01
     Colts
    0.90
     Wire
    0.87
     City
    0.87
     County
    0.85
     Hopkins
    0.81
     Citiz
    0.79
     Harbor
    0.79
     Yards
    0.79
    Activations Density 0.011%

    No Known Activations