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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11769
    Prev
    Next
    INDEX
    Explanations

    call-to-action phrases, particularly related to subscribing or registering

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a call to action or subscription prompts

    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
    Magikarp
    -0.69
    naire
    -0.64
     absent
    -0.63
    hesis
    -0.62
    should
    -0.60
     palate
    -0.59
     CPC
    -0.57
    âĨij
    -0.57
     absence
    -0.57
     disson
    -0.57
    POSITIVE LOGITS
    cloneembedreportprint
    0.98
     Vanity
    0.76
    TING
    0.73
    chell
    0.73
     ready
    0.73
     cele
    0.69
     Directions
    0.69
     notified
    0.68
    ActionCode
    0.67
    daily
    0.67
    Activations Density 0.029%

    No Known Activations