Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13472
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Owens"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, especially names related to individuals or entities

    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
    acters
    -0.73
    bang
    -0.64
    âĸ¬
    -0.64
    plane
    -0.64
    boards
    -0.63
    ancial
    -0.62
    ministic
    -0.61
    flies
    -0.60
    iard
    -0.60
    ners
    -0.60
    POSITIVE LOGITS
    yssey
    1.00
    cean
    0.96
    toc
    0.79
    scill
    0.79
    ceans
    0.79
    sett
    0.75
    oga
    0.74
    chemy
    0.70
    pport
    0.70
    ensibly
    0.69
    Activations Density 0.128%

    No Known Activations