© 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. 0-RES-JB
    11. 9985
    Prev
    Next
    INDEX
    Explanations

    words related to something being fastened or repaired

    oai_token-act-pair · gpt-3.5-turbo

    references to fixed terms or fixed values in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emin
    -0.83
    assic
    -0.77
    assing
    -0.73
    ather
    -0.71
    OHN
    -0.68
     Tears
    -0.68
    AMY
    -0.68
    ittle
    -0.67
    assin
    -0.66
    ÃŃa
    -0.65
    POSITIVE LOGITS
     fixed
    3.77
    fixed
    2.86
     Fixed
    2.19
    Fixed
    2.11
     fix
    1.66
     fixing
    1.61
     FIX
    1.61
     fixes
    1.57
     corrected
    1.46
     repaired
    1.42
    Activations Density 0.013%

    No Known Activations