© 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. 10-RES-JB
    11. 3046
    Prev
    Next
    INDEX
    Explanations

    words related to criticism or negative judgment

    oai_token-act-pair · gpt-3.5-turbo

    instances of words containing the prefix "ob" or words related to obsolescence and obstacles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gas
    -0.83
     guiActiveUnfocused
    -0.73
    EngineDebug
    -0.72
    agne
    -0.72
     Birch
    -0.66
     gases
    -0.64
     resort
    -0.63
     unemployment
    -0.62
    ivities
    -0.62
     Carlson
    -0.61
    POSITIVE LOGITS
    lique
    1.51
    livion
    1.42
    amacare
    1.42
    structed
    1.35
    nox
    1.34
    fusc
    1.30
    vious
    1.29
    solete
    1.29
    eyed
    1.20
    taining
    1.17
    Activations Density 0.024%

    No Known Activations