© 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. 18870
    Prev
    Next
    INDEX
    Explanations

    phrases related to data collection and surveillance activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to data collection and surveillance practices

    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
     Purg
    -0.76
    Finish
    -0.68
     Destroyer
    -0.67
     Presbyter
    -0.67
    FontSize
    -0.67
     Chaser
    -0.65
    undai
    -0.65
     Carbuncle
    -0.64
    ModLoader
    -0.64
    nesday
    -0.64
    POSITIVE LOGITS
     information
    1.59
     data
    1.54
    information
    1.25
     info
    1.23
     metadata
    1.18
     insights
    1.18
     datasets
    1.15
     INFORMATION
    1.11
     confidential
    1.10
     passwords
    1.09
    Activations Density 0.377%

    No Known Activations