© 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. 3-RES-JB
    11. 4809
    Prev
    Next
    INDEX
    Explanations

    phrases related to the legalization of various substances or activities, particularly focusing on marijuana

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legalization and law

    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
    selage
    -0.84
    erella
    -0.80
    voy
    -0.76
    auga
    -0.76
    inous
    -0.70
    yip
    -0.69
    ortment
    -0.65
    ngth
    -0.64
    iler
    -0.64
    zinski
    -0.63
    POSITIVE LOGITS
    enforcement
    0.77
     cartel
    0.75
     racket
    0.74
     fees
    0.74
     precedent
    0.73
     justices
    0.73
     jurisdiction
    0.68
     CTR
    0.66
     ACTIONS
    0.65
     rulings
    0.65
    Activations Density 0.313%

    No Known Activations