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. 19610
    Prev
    Next
    INDEX
    Explanations

    phrases related to newsletter subscriptions and email updates

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subscription services and newsletters

    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
    mens
    -0.74
    ULTS
    -0.72
    =]
    -0.68
    erent
    -0.63
    othal
    -0.62
    iewicz
    -0.62
     convinc
    -0.60
    gger
    -0.59
    dies
    -0.58
    REDACTED
    -0.58
    POSITIVE LOGITS
    romeda
    0.86
    iframe
    0.66
    rew
    0.64
    taboola
    0.64
     subscribe
    0.61
     widgets
    0.60
    rid
    0.60
     permissions
    0.56
    oslov
    0.56
    thumbnails
    0.55
    Activations Density 0.031%

    No Known Activations