© 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. 21120
    Prev
    Next
    INDEX
    Explanations

    references to a legal act named the Hatch Act

    oai_token-act-pair · gpt-3.5-turbo

    references to the Hatch Act

    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
     periphery
    -0.75
    icably
    -0.66
    OX
    -0.64
    isance
    -0.63
    etheless
    -0.61
    pez
    -0.60
     occas
    -0.59
     sclerosis
    -0.59
     peer
    -0.59
     ECB
    -0.58
    POSITIVE LOGITS
     Hatch
    1.25
    lings
    1.20
    aday
    0.97
    buck
    0.92
    mong
    0.88
    ns
    0.86
    intosh
    0.86
    craft
    0.85
    bral
    0.84
    bone
    0.83
    Activations Density 0.006%

    No Known Activations