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. 19867
    Prev
    Next
    INDEX
    Explanations

    instances where an email address is mentioned or requested

    oai_token-act-pair · gpt-3.5-turbo

    content related to email addresses and validation

    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
    ourced
    -0.66
    fig
    -0.66
    gra
    -0.61
     ANG
    -0.61
     benchmarks
    -0.61
    raq
    -0.60
    vs
    -0.59
    iev
    -0.59
    Scene
    -0.59
     internally
    -0.59
    POSITIVE LOGITS
    PsyNetMessage
    0.93
    Password
    0.91
     Password
    0.83
    Zip
    0.78
    password
    0.77
     Whats
    0.77
    Fax
    0.74
     Send
    0.74
     Gmail
    0.73
    âĢ¢âĢ¢
    0.69
    Activations Density 0.056%

    No Known Activations