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. 3-RES-JB
    6. 14885
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer processors, specifically focusing on the "Kaby Lake" series

    oai_token-act-pair · gpt-3.5-turbo

    names and variations of the word "baby"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iveness
    -0.84
    ivity
    -0.83
    encing
    -0.75
    fully
    -0.73
    aciously
    -0.73
    ively
    -0.72
    endiary
    -0.70
    urious
    -0.69
    psons
    -0.69
     pity
    -0.69
    POSITIVE LOGITS
    aby
    0.99
    ħĭ
    0.73
    rics
    0.72
    aroo
    0.71
    ovic
    0.70
    butt
    0.70
     Isles
    0.69
    >>>>>>>>
    0.68
     Joyce
    0.68
     quo
    0.66
    Activations Density 0.005%

    No Known Activations