© 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. 10-RES-JB
    11. 2841
    Prev
    Next
    INDEX
    Explanations

    personal identifying information like names, addresses, credit card details, and email addresses

    oai_token-act-pair · gpt-3.5-turbo

    references to private or personal information and identifiers

    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
     Democr
    -0.78
    Adds
    -0.63
    iva
    -0.62
    Impro
    -0.62
    Rex
    -0.61
    SUP
    -0.61
    conservative
    -0.61
    Better
    -0.60
    impl
    -0.59
    binding
    -0.58
    POSITIVE LOGITS
     nationality
    1.25
     surname
    1.22
     location
    1.20
    estamp
    1.13
     date
    1.13
     initials
    1.12
     address
    1.10
     birthplace
    1.06
     approximate
    1.04
     Location
    1.04
    Activations Density 0.236%

    No Known Activations