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. 4359
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory information

    oai_token-act-pair · gpt-3.5-turbo

    text related to legal amendments and legislative changes

    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
    elist
    -0.55
     Spoiler
    -0.53
     Paste
    -0.51
    atural
    -0.50
     spoiler
    -0.50
     Blu
    -0.49
    terday
    -0.49
     Polo
    -0.49
    andowski
    -0.47
    ifference
    -0.47
    POSITIVE LOGITS
    arag
    0.61
    raising
    0.54
    ansson
    0.48
    anna
    0.45
    meter
    0.44
    mn
    0.44
     next
    0.44
    externalActionCode
    0.43
    un
    0.43
    aged
    0.43
    Activations Density 0.306%

    No Known Activations