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. 20991
    Prev
    Next
    INDEX
    Explanations

    events or actions related to various happenings and movements, including training, supplies distribution, research, debates, and sports

    oai_token-act-pair · gpt-3.5-turbo

    events and activities related to education and community effort

    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
     hindsight
    -0.76
    -)
    -0.66
     caveat
    -0.64
     exceptions
    -0.58
     dislike
    -0.57
     downside
    -0.56
     caveats
    -0.54
     Kardash
    -0.53
     things
    -0.53
     innocence
    -0.53
    POSITIVE LOGITS
    .[
    1.12
    .''.
    1.10
     respectively
    1.03
    .
    1.00
    .</
    0.98
    .(
    0.96
    .<
    0.90
    .–
    0.88
    .#
    0.87
    .ãĢį
    0.84
    Activations Density 0.968%

    No Known Activations