© 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. 9-RES-JB
    11. 18361
    Prev
    Next
    INDEX
    Explanations

    phrases related to unchecked, unhindered, or unregulated activities

    oai_token-act-pair · gpt-3.5-turbo

    variations of the prefix "un-" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    udeb
    -0.80
    Clar
    -0.77
     toget
    -0.73
    eatures
    -0.73
    ioxide
    -0.71
    vertisement
    -0.70
    bourg
    -0.70
    tti
    -0.67
    ucc
    -0.65
    ©¶æ
    -0.65
    POSITIVE LOGITS
    uality
    0.72
    aneous
    0.72
    ly
    0.72
    adoes
    0.72
     bias
    0.64
    aneously
    0.63
     baggage
    0.63
     Territories
    0.62
     manslaughter
    0.61
    ness
    0.60
    Activations Density 0.128%

    No Known Activations