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. 23509
    Prev
    Next
    INDEX
    Explanations

    keywords related to breast health

    oai_token-act-pair · gpt-3.5-turbo

    references to breast cancer and breast-related topics

    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
    pmwiki
    -0.84
    umar
    -0.78
    ADRA
    -0.77
    ourning
    -0.76
    govtrack
    -0.72
    ahime
    -0.70
    ournal
    -0.70
    quickShipAvailable
    -0.69
    arta
    -0.66
    mble
    -0.65
    POSITIVE LOGITS
    plate
    1.10
    fed
    1.06
    bone
    1.01
     implants
    1.00
     milk
    0.96
     breasts
    0.95
    mil
    0.92
     nipples
    0.91
     breast
    0.89
    plates
    0.87
    Activations Density 0.012%

    No Known Activations