© 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. 7890
    Prev
    Next
    INDEX
    Explanations

    actions related to communication such as sending messages, emails, texts, and mails

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sending messages or communications

    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
     facets
    -0.73
     pores
    -0.71
    existing
    -0.69
     disadvantages
    -0.69
     similarities
    -0.69
    shed
    -0.67
    ptions
    -0.67
     aspects
    -0.66
    asse
    -0.65
     ceilings
    -0.65
    POSITIVE LOGITS
     message
    1.22
     mail
    1.11
     email
    1.10
     congrat
    1.10
     SMS
    1.09
     emails
    1.09
     messages
    1.09
     letter
    1.07
     invitations
    1.06
     Emails
    1.00
    Activations Density 0.134%

    No Known Activations