© 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. 0-RES-JB
    11. 15319
    Prev
    Next
    INDEX
    Explanations

    words related to transparency and open communication

    oai_token-act-pair · gpt-3.5-turbo

    the concept of transparency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sutton
    -0.79
     Weekend
    -0.75
    ruck
    -0.72
    Age
    -0.72
     Heights
    -0.70
     Eaton
    -0.69
     Temper
    -0.68
    beat
    -0.66
    age
    -0.66
     Bomber
    -0.66
    POSITIVE LOGITS
     transparent
    3.57
     opaque
    2.17
     transparency
    2.12
     translucent
    1.92
     Transparency
    1.66
    parency
    1.40
     opacity
    1.30
     reflective
    1.24
     seamless
    1.20
     flexible
    1.11
    Activations Density 0.020%

    No Known Activations