Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 20901
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscribing to newsletters

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to newsletter subscription and account management

    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
    omorphic
    -0.68
    imer
    -0.60
     Hein
    -0.58
     prototyp
    -0.58
    ums
    -0.57
    github
    -0.56
    aimon
    -0.55
    nut
    -0.54
    ilities
    -0.54
    ovember
    -0.54
    POSITIVE LOGITS
    interstitial
    0.93
     Cancel
    0.72
    $$$$
    0.67
     Invalid
    0.67
    herence
    0.64
     Que
    0.62
    Subscribe
    0.58
     Accept
    0.57
     Dinner
    0.56
     Reload
    0.56
    Activations Density 0.016%

    No Known Activations