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. 8-RES-JB
    6. 6664
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the term "Rad"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Rad" and its variations related to radiation or radiation-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORTS
    -0.73
    urities
    -0.66
    ãĥīãĥ©
    -0.65
    theless
    -0.64
     plantation
    -0.62
     kneeling
    -0.61
     Speedway
    -0.61
    eff
    -0.60
    redits
    -0.58
     waivers
    -0.58
    POSITIVE LOGITS
    iation
    1.23
    iance
    1.19
    iated
    1.18
    iate
    1.11
    isson
    1.04
    cliffe
    1.03
    icals
    1.02
    iator
    1.00
    iant
    1.00
    itional
    0.99
    Activations Density 0.031%

    No Known Activations