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. 24246
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Simpson."

    oai_token-act-pair · gpt-3.5-turbo

    references to the character Simpson from "The Simpsons."

    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
    arians
    -0.81
    warm
    -0.75
    places
    -0.74
    inventoryQuantity
    -0.70
    arian
    -0.70
    istant
    -0.69
    enser
    -0.69
    ensable
    -0.68
    href
    -0.66
    RAW
    -0.66
    POSITIVE LOGITS
     Simpson
    1.19
    pson
    1.01
    psons
    0.79
     Clause
    0.76
    inez
    0.72
    shire
    0.68
    mania
    0.67
    dale
    0.67
    lich
    0.66
    ultane
    0.66
    Activations Density 0.010%

    No Known Activations