© 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. 11170
    Prev
    Next
    INDEX
    Explanations

    emails containing potentially sensitive information or messages involving a security breach or classified material

    oai_token-act-pair · gpt-3.5-turbo

    references to emails, particularly in a political context

    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
    axis
    -0.86
    SHIP
    -0.71
    stad
    -0.70
    iasis
    -0.69
    Interstitial
    -0.69
    iculture
    -0.69
    culosis
    -0.68
    INAL
    -0.67
    sole
    -0.67
    adic
    -0.65
    POSITIVE LOGITS
     leaked
    1.04
     pertaining
    1.02
     declass
    0.94
     relating
    0.93
    heet
    0.92
     trove
    0.90
     dumps
    0.88
     Emails
    0.87
     transcripts
    0.87
     stored
    0.86
    Activations Density 0.104%

    No Known Activations