© 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. 608
    Prev
    Next
    INDEX
    Explanations

    words related to legal or military titles

    oai_token-act-pair · gpt-3.5-turbo

    the term "ley" in various contexts

    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
    ãĥķãĤ©
    -0.80
    ebus
    -0.79
    ¥ŀ
    -0.78
    utenberg
    -0.78
    icist
    -0.75
    atoon
    -0.74
    ilers
    -0.73
    insula
    -0.73
    umers
    -0.73
    umat
    -0.72
    POSITIVE LOGITS
    wood
    1.08
    wine
    1.01
    bridge
    1.00
    dale
    0.94
    fleet
    0.88
    corn
    0.88
    ley
    0.83
    WOOD
    0.82
    bury
    0.80
    puff
    0.79
    Activations Density 0.031%

    No Known Activations