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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16655
    Prev
    Next
    INDEX
    Explanations

    texts related to signing up for digital access and receiving offers

    oai_token-act-pair · gpt-3.5-turbo

    phrases and components related to promotional offers and subscription information

    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
    beit
    -0.79
     Aki
    -0.70
     pav
    -0.69
     plurality
    -0.68
    worn
    -0.65
    âĶ
    -0.61
    xual
    -0.60
    soType
    -0.60
    oris
    -0.57
    ourgeois
    -0.57
    POSITIVE LOGITS
     FREE
    1.18
     alerts
    0.99
    Newsletter
    0.94
    FREE
    0.88
     newsletter
    0.86
     coupon
    0.86
     ebook
    0.84
     personalized
    0.83
     notifications
    0.82
     Subscribe
    0.81
    Activations Density 0.186%

    No Known Activations