© 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. 8-RES-JB
    11. 632
    Prev
    Next
    INDEX
    Explanations

    calls to action prompting signing up or joining something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to signing up or subscriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Coul
    -0.66
     Himself
    -0.64
    ãĥīãĥ©ãĤ´ãĥ³
    -0.62
    ļé
    -0.61
     Galile
    -0.60
     Lumpur
    -0.59
    uma
    -0.57
    Reloaded
    -0.57
    knife
    -0.56
     Gravity
    -0.56
    POSITIVE LOGITS
     alerts
    0.71
     âĸ
    0.65
     Submit
    0.64
     newsletter
    0.62
     listener
    0.62
    ESPN
    0.61
    scribe
    0.60
    ancy
    0.59
    lish
    0.59
    ername
    0.59
    Activations Density 0.024%

    No Known Activations