© 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. 6755
    Prev
    Next
    INDEX
    Explanations

    expressions related to subscribing to newsletters or news updates

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing gratitude related to subscriptions

    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
     tant
    -0.60
     reluct
    -0.60
     conclud
    -0.58
     seiz
    -0.58
     resil
    -0.58
     accomp
    -0.54
     charact
    -0.54
     indist
    -0.53
     misunder
    -0.53
     lone
    -0.51
    POSITIVE LOGITS
     subscribing
    1.01
    Subscribe
    0.71
    iframe
    0.70
     subscribe
    0.68
    ceive
    0.65
     Subscribe
    0.65
    inion
    0.64
     subscription
    0.62
    abc
    0.62
     subscriptions
    0.60
    Activations Density 0.024%

    No Known Activations