© 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. 22451
    Prev
    Next
    INDEX
    Explanations

    prompts to engage with content, such as leaving comments, following on social media, and sharing

    oai_token-act-pair · gpt-3.5-turbo

    calls to action encouraging audience engagement

    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
    hematic
    -0.71
    paren
    -0.69
    examination
    -0.67
    Orig
    -0.66
    ãĤ´ãĥ³
    -0.66
    MpServer
    -0.64
    £ı
    -0.64
    åħī
    -0.63
    aukee
    -0.63
    housing
    -0.62
    POSITIVE LOGITS
     subscribe
    1.46
     Subscribe
    1.35
     bookmark
    1.18
     Follow
    1.17
    Subscribe
    1.14
     follow
    1.10
     subscribed
    1.08
     LIKE
    1.06
     subscribing
    1.05
     retweet
    1.03
    Activations Density 0.154%

    No Known Activations