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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13537
    Prev
    Next
    INDEX
    Explanations

    email-related strings and prompts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to email addresses and their validation status

    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
    FTWARE
    -0.69
    gat
    -0.67
    wired
    -0.66
    olini
    -0.64
    cow
    -0.61
    ¶
    -0.60
    nil
    -0.60
    bang
    -0.59
     cel
    -0.58
    chio
    -0.57
    POSITIVE LOGITS
     Travels
    0.68
     LinkedIn
    0.63
     Premium
    0.63
     Pinterest
    0.63
     pauses
    0.62
     Amendments
    0.61
     Seller
    0.61
     Marketplace
    0.60
     Send
    0.60
    Privacy
    0.60
    Activations Density 0.104%

    No Known Activations