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. 12930
    Prev
    Next
    INDEX
    Explanations

    sentences ending with period ("."), possibly related to news articles or formal communication

    oai_token-act-pair · gpt-3.5-turbo

    instances of quantifiable statistics or metrics

    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
     metic
    -0.62
    ©¶æ
    -0.57
     Yates
    -0.54
    soever
    -0.54
    backer
    -0.53
     Tenth
    -0.52
     Grayson
    -0.52
     standpoint
    -0.52
     JJ
    -0.52
     opposed
    -0.51
    POSITIVE LOGITS
    Scroll
    0.78
    dden
    0.77
    à¼
    0.67
    isine
    0.66
     marrow
    0.64
    使
    0.63
    Ur
    0.62
    Newsletter
    0.60
    iru
    0.60
    Such
    0.59
    Activations Density 0.306%

    No Known Activations