© 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 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. 9-RES-JB
    11. 18307
    Prev
    Next
    INDEX
    Explanations

    phrases related to legislation, government actions, and political discussions

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns or phrases indicating governance or regulatory actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     namely
    -0.87
    aciously
    -0.85
     suppose
    -0.82
    ingly
    -0.77
    eat
    -0.69
    perhaps
    -0.69
     preceded
    -0.68
    rix
    -0.67
    handled
    -0.66
    eyed
    -0.65
    POSITIVE LOGITS
     remainder
    1.29
     next
    1.09
     entirety
    1.09
     2019
    1.03
     entire
    1.01
     upcoming
    1.01
     same
    1.00
     remaining
    0.98
     fullest
    0.97
     2024
    0.95
    Activations Density 0.513%

    No Known Activations