© 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. 3-RES-JB
    11. 710
    Prev
    Next
    INDEX
    Explanations

    verbs related to the process of creating laws or regulations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "enact" and its variations, indicating a focus on legislative action and policy implementation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mub
    -0.70
    Tur
    -0.69
     9000
    -0.68
    afa
    -0.67
     Stain
    -0.67
     Hav
    -0.65
     Turk
    -0.65
    Lens
    -0.63
     Plane
    -0.63
     Wit
    -0.63
    POSITIVE LOGITS
     enacted
    1.08
    eering
    0.95
     enact
    0.94
    sylvania
    0.89
    ãĥ¼ãĥĨãĤ£
    0.87
    ments
    0.85
    urally
    0.84
     decree
    0.80
    æĸ¹
    0.76
    insula
    0.75
    Activations Density 0.014%

    No Known Activations