© 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. 661
    Prev
    Next
    INDEX
    Explanations

    phrases related to laws and regulations taking effect

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the implementation of laws or regulations

    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
    IDES
    -0.67
     Malt
    -0.65
     substr
    -0.63
     Pitch
    -0.63
    asca
    -0.61
     Rhythm
    -0.61
     Knot
    -0.61
     skies
    -0.60
     Trout
    -0.59
    cin
    -0.59
    POSITIVE LOGITS
    uel
    0.96
    iveness
    0.87
    uate
    0.83
    ively
    0.83
    effects
    0.83
    uating
    0.81
    ful
    0.80
    uated
    0.79
    ually
    0.79
    ual
    0.78
    Activations Density 0.033%

    No Known Activations