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. 4385
    Prev
    Next
    INDEX
    Explanations

    subscriptions or prompts to subscribe to services or newsletters

    oai_token-act-pair · gpt-3.5-turbo

    commands or prompts related to subscribing to services

    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
     Ezek
    -0.59
    ccording
    -0.58
    amily
    -0.56
    had
    -0.56
    hemy
    -0.55
    ailability
    -0.54
    emale
    -0.54
    Documents
    -0.51
     thous
    -0.50
    rehens
    -0.50
    POSITIVE LOGITS
     to
    0.77
    thumbnails
    0.70
    uler
    0.69
    externalActionCode
    0.66
     isEnabled
    0.60
    rils
    0.60
     securely
    0.55
     antioxid
    0.54
    PLIED
    0.54
    º
    0.52
    Activations Density 0.014%

    No Known Activations