© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 23237
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreeing to receive updates or offers via email

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subscription or opt-in agreements

    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
     Catal
    -0.65
    gypt
    -0.65
    ylum
    -0.62
     Columb
    -0.57
    bourg
    -0.57
    berra
    -0.56
     Brend
    -0.56
     Gall
    -0.55
    conn
    -0.53
     Hood
    -0.53
    POSITIVE LOGITS
     occasional
    1.01
    owship
    0.73
     periodic
    0.73
     notifications
    0.71
     acknowled
    0.67
    NEWS
    0.64
    Daily
    0.63
    Material
    0.62
     emails
    0.61
    ZE
    0.59
    Activations Density 0.026%

    No Known Activations