© 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. 11-RES-JB
    11. 11677
    Prev
    Next
    INDEX
    Explanations

    legal or penalty-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to penalties, legal and regulatory actions, and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ween
    -0.73
    gall
    -0.71
    perty
    -0.68
     Typh
    -0.67
    ugen
    -0.65
    âĹ¼
    -0.65
    Beaut
    -0.62
    ocrates
    -0.60
     Know
    -0.59
    oyal
    -0.59
    POSITIVE LOGITS
     lasts
    1.22
     stems
    1.20
     lasted
    1.15
     stemmed
    1.15
     coincides
    1.12
     occurred
    1.11
     applies
    1.11
     occurs
    1.11
     involves
    1.10
     consisted
    1.07
    Activations Density 0.342%

    No Known Activations