Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 13004
    Prev
    Next
    INDEX
    Explanations

    email addresses or references to email communication

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "email" and related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artifacts
    -0.73
     idols
    -0.72
    ãĥİ
    -0.68
     Hats
    -0.67
     landmarks
    -0.62
     Flags
    -0.62
    orsche
    -0.61
    Os
    -0.61
    Mods
    -0.58
    arts
    -0.58
    POSITIVE LOGITS
     correspondence
    1.07
     reply
    1.03
     statement
    1.01
     response
    0.96
     newsletter
    0.95
     address
    0.95
     message
    0.93
     invitation
    0.90
     inbox
    0.89
     exchange
    0.88
    Activations Density 0.045%

    No Known Activations