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. 10-RES-JB
    6. 17849
    Prev
    Next
    INDEX
    Explanations

    terms related to medical issues and traumatic events, particularly those involving pregnancies and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    topics related to miscarriage and reproductive health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     organis
    -0.70
     organise
    -0.70
     organisations
    -0.68
     favourites
    -0.66
    sbm
    -0.63
    These
    -0.61
     NGOs
    -0.61
    artments
    -0.60
     redund
    -0.59
     announcements
    -0.58
    POSITIVE LOGITS
     Adolf
    0.74
     himself
    0.73
     afterward
    0.68
     his
    0.67
     Scalia
    0.67
    his
    0.64
    —"
    0.61
     Spock
    0.61
     him
    0.61
     "'
    0.61
    Activations Density 1.139%

    No Known Activations