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. 11-RES-JB
    6. 18262
    Prev
    Next
    INDEX
    Explanations

    dates and time references

    oai_token-act-pair · gpt-3.5-turbo

    references to fundraising or financial topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cooldown
    -0.72
     distraction
    -0.64
     Complex
    -0.63
    Dialogue
    -0.63
    France
    -0.63
    imil
    -0.62
    ZI
    -0.61
    ../
    -0.60
    Italy
    -0.60
    #
    -0.60
    POSITIVE LOGITS
    ²¾
    1.10
     sure
    0.68
    uth
    0.66
    plin
    0.64
    lihood
    0.63
    leans
    0.62
    é¾įå¥ij士
    0.61
     whatsoever
    0.61
    alde
    0.61
    cipled
    0.60
    Activations Density 0.000%

    No Known Activations