© 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. 6-RES-JB
    11. 11833
    Prev
    Next
    INDEX
    Explanations

    references to "du" followed by another word

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "du" indicating a focus on specific cultural or artistic references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IO
    -0.79
    LER
    -0.72
    ULE
    -0.71
    ANS
    -0.70
    IAL
    -0.70
    ATTLE
    -0.69
    acco
    -0.69
    mable
    -0.68
    nor
    -0.68
    undle
    -0.68
    POSITIVE LOGITS
     jour
    0.88
     masse
    0.73
     dé
    0.70
     gou
    0.69
    bone
    0.68
     lieu
    0.68
    ction
    0.68
    ught
    0.67
    ivery
    0.65
     wool
    0.65
    Activations Density 0.017%

    No Known Activations