© 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. 7-RES-JB
    11. 3058
    Prev
    Next
    INDEX
    Explanations

    phone numbers or numerical identifiers in text

    oai_token-act-pair · gpt-3.5-turbo

    references to telephone and identification numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    romeda
    -0.79
    rike
    -0.76
    reci
    -0.72
    ipation
    -0.70
    ovie
    -0.69
    ittle
    -0.68
    opot
    -0.68
    gewater
    -0.68
    ilib
    -0.67
    retty
    -0.67
    POSITIVE LOGITS
     passwords
    0.91
    plates
    0.87
     password
    0.86
     generator
    0.86
     login
    0.86
     registration
    0.85
     belonging
    0.83
     identifier
    0.83
     authentication
    0.82
     username
    0.82
    Activations Density 0.112%

    No Known Activations