© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 2369
    Prev
    Next
    INDEX
    Explanations

    phrases related to advertisements or announcements

    oai_token-act-pair · gpt-3.5-turbo

    suffixes related to various forms of announcements or regular features in content

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

    No Comments

    Negative Logits
    itsch
    -0.70
     instinct
    -0.69
    onics
    -0.69
    iv
    -0.68
     alienated
    -0.67
    anship
    -0.66
    anski
    -0.65
    imb
    -0.65
    otom
    -0.65
    gling
    -0.64
    POSITIVE LOGITS
     Releases
    0.87
     Videos
    0.77
     Updates
    0.75
    peak
    0.73
     Seller
    0.70
    çīĪ
    0.68
     Recomm
    0.68
     Era
    0.68
     Thumbnails
    0.67
    Discussion
    0.67
    Activations Density 0.103%

    No Known Activations