© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 8749
    Prev
    Next
    INDEX
    Explanations

    numbers potentially related to quantities or rankings

    oai_token-act-pair · gpt-3.5-turbo

    numerical data relating to quantities or categories

    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
    matter
    -0.87
     Akin
    -0.68
    Url
    -0.66
    charge
    -0.66
    Emb
    -0.66
    Stock
    -0.64
    Kar
    -0.63
    agement
    -0.62
    à¥
    -0.60
    ighter
    -0.60
    POSITIVE LOGITS
     finalists
    0.87
     ways
    0.71
     remaining
    0.69
     siblings
    0.69
     quir
    0.68
    acea
    0.68
    teenth
    0.68
    oggle
    0.65
    irtual
    0.65
     authorized
    0.65
    Activations Density 0.067%

    No Known Activations