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. 5331
    Prev
    Next
    INDEX
    Explanations

    terms related to businesses and organizations that are family-owned or family-friendly

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to family structures and family-oriented themes

    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
    hole
    -0.72
    iov
    -0.70
    umatic
    -0.69
    hol
    -0.68
    shit
    -0.68
    wagen
    -0.66
    issan
    -0.65
    ovsky
    -0.65
    henko
    -0.63
    claw
    -0.63
    POSITIVE LOGITS
     belongings
    0.72
     caregivers
    0.71
     kindred
    0.70
     elders
    0.67
     Weston
    0.67
     mourning
    0.66
     holiday
    0.65
     reunion
    0.65
     bond
    0.65
     ravaged
    0.65
    Activations Density 0.271%

    No Known Activations