© 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. 22987
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to personal and sensitive information

    oai_token-act-pair · gpt-3.5-turbo

    terms related to personal and sensitive information

    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
    unct
    -0.75
    STRUCT
    -0.74
    ajor
    -0.73
     McDonnell
    -0.70
    ocal
    -0.69
     benches
    -0.69
    Leader
    -0.68
    GBT
    -0.68
    Sound
    -0.68
    Interstitial
    -0.66
    POSITIVE LOGITS
     collected
    0.98
     inappropriately
    0.95
     passwords
    0.93
     breaches
    0.92
     belonging
    0.89
     unlawfully
    0.87
     encrypted
    0.85
     stored
    0.85
     privacy
    0.82
     transf
    0.82
    Activations Density 0.078%

    No Known Activations