© 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. 8-RES-JB
    11. 11661
    Prev
    Next
    INDEX
    Explanations

    terms related to leftovers or byproducts

    oai_token-act-pair · gpt-3.5-turbo

    references to food production and ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "]=>
    -0.73
    "!
    -0.69
     sanity
    -0.69
     behavi
    -0.68
    Conclusion
    -0.67
    !".
    -0.66
    eries
    -0.65
    ]."
    -0.65
    icult
    -0.65
    CONCLUS
    -0.64
    POSITIVE LOGITS
     ancestor
    0.74
     precursor
    0.66
     predecessor
    0.62
    ©¶æ
    0.61
     pictured
    0.60
    picked
    0.59
     cartridge
    0.59
     Macron
    0.58
     fraction
    0.57
     minus
    0.56
    Activations Density 1.309%

    No Known Activations