© 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. 446
    Prev
    Next
    INDEX
    Explanations

    phrases related to signing up for newsletters or services

    oai_token-act-pair · gpt-3.5-turbo
    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
     surfaces
    -0.70
     pav
    -0.70
    ppings
    -0.69
    ifice
    -0.69
    ibia
    -0.66
     depiction
    -0.64
     nudity
    -0.64
    angible
    -0.63
     sculpture
    -0.63
     portrays
    -0.63
    POSITIVE LOGITS
     newsletter
    1.66
     Newsletter
    1.65
     mailing
    1.28
     newsletters
    1.26
    letters
    1.24
     alerts
    1.18
    letter
    1.13
     Telegram
    1.13
     email
    1.08
     subscription
    1.08
    Activations Density 0.090%

    No Known Activations