© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18840
    Prev
    Next
    INDEX
    Explanations

    information related to data tracking and privacy concerns, particularly in the context of voice recognition technology

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to data collection and privacy policies

    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
     quart
    -0.74
     dudes
    -0.70
     cops
    -0.69
     bosses
    -0.66
     generals
    -0.66
     suprem
    -0.66
     pont
    -0.64
     drummer
    -0.64
     Italians
    -0.63
     reckoned
    -0.62
    POSITIVE LOGITS
     Privacy
    1.02
     Please
    1.01
     Cookies
    0.99
     Sponsor
    0.99
     Site
    0.98
     cookies
    0.97
     Terms
    0.94
    Please
    0.90
     Website
    0.89
     SERVICES
    0.88
    Activations Density 0.526%

    No Known Activations