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. 22821
    Prev
    Next
    INDEX
    Explanations

    specific phone numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and their associated context, particularly in reference to addresses or contact information

    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
    ensibly
    -0.78
    iaries
    -0.72
    ²¾
    -0.64
    dust
    -0.64
    redients
    -0.63
    ables
    -0.62
    artisan
    -0.61
    Īè
    -0.59
    pled
    -0.57
    phia
    -0.57
    POSITIVE LOGITS
     ext
    1.16
    Fax
    0.96
     fax
    0.93
     Extension
    0.76
     Ext
    0.75
     Toll
    0.75
     Alternatively
    0.73
     Email
    0.71
    EMA
    0.70
     UNCLASSIFIED
    0.68
    Activations Density 0.028%

    No Known Activations