© 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. 19052
    Prev
    Next
    INDEX
    Explanations

    words related to conflict or opposition between different entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "and."

    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
    Discuss
    -0.84
    oren
    -0.73
    Reviewed
    -0.72
    ((
    -0.72
    oops
    -0.71
    ï¸
    -0.71
    ................................................................
    -0.71
    notations
    -0.71
    huge
    -0.70
    \.
    -0.70
    POSITIVE LOGITS
     ours
    0.94
     its
    0.87
     hers
    0.87
     theirs
    0.87
     the
    0.78
     actual
    0.78
     those
    0.77
     yours
    0.75
     their
    0.68
     non
    0.67
    Activations Density 0.141%

    No Known Activations