© 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. 6-RES-JB
    11. 23716
    Prev
    Next
    INDEX
    Explanations

    terms related to difficult choices or contradictory situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dilemmas and paradoxes

    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
    rations
    -0.86
    ewitness
    -0.81
    azeera
    -0.79
    baugh
    -0.77
    vation
    -0.76
    ghai
    -0.72
    endar
    -0.70
    athering
    -0.70
    gio
    -0.69
    achers
    -0.68
    POSITIVE LOGITS
    undrum
    1.09
     dilemma
    1.07
     paradox
    1.03
    otom
    0.87
     Paradox
    0.86
    otomy
    0.81
    ioned
    0.78
     solved
    0.76
     dile
    0.76
     mund
    0.75
    Activations Density 0.053%

    No Known Activations