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. 8-RES-JB
    6. 3560
    Prev
    Next
    INDEX
    Explanations

    words related to legal and governmental terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to agreements or official announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forces
    -0.55
    eret
    -0.53
     fortune
    -0.49
    checks
    -0.48
     clamp
    -0.48
    ometimes
    -0.47
    kefeller
    -0.47
    amins
    -0.47
    anches
    -0.46
    taboola
    -0.46
    POSITIVE LOGITS
    ultimate
    0.66
    ciation
    0.64
    Reviewer
    0.56
    uesday
    0.56
    Tube
    0.56
     titled
    0.53
     {*
    0.50
    arez
    0.48
    667
    0.48
     Heads
    0.48
    Activations Density 1.616%

    No Known Activations