© 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 EvalsExportsinterp-engineNEWAPI 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. 19064
    Prev
    Next
    INDEX
    Explanations

    words related to policies, regulations, or laws

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to regulations, policies, and governance

    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
    tis
    -0.72
    laughs
    -0.71
    else
    -0.62
     likes
    -0.60
     Quit
    -0.56
    wise
    -0.56
    Else
    -0.54
    needs
    -0.54
     thinks
    -0.54
    Recomm
    -0.54
    POSITIVE LOGITS
     include
    1.31
     were
    1.30
     are
    1.29
     contain
    1.26
     represent
    1.22
     aren
    1.21
     comprise
    1.20
     involve
    1.20
     weren
    1.20
     consist
    1.18
    Activations Density 0.304%

    No Known Activations