© 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. 9-RES-JB
    11. 4339
    Prev
    Next
    INDEX
    Explanations

    mentions of executive orders

    oai_token-act-pair · gpt-3.5-turbo
    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
    dden
    -0.78
     Argon
    -0.73
     Continent
    -0.71
    rose
    -0.70
     Wit
    -0.67
    istics
    -0.64
    CTV
    -0.63
     Passion
    -0.62
    zzy
    -0.62
     Cats
    -0.61
    POSITIVE LOGITS
     authorizing
    1.20
     prohibiting
    1.19
     banning
    1.13
     restricting
    1.09
     issued
    1.03
     barring
    1.00
     forb
    0.98
     granting
    0.98
     limiting
    0.97
     legalizing
    0.96
    Activations Density 0.111%

    No Known Activations