© 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. 8-RES-JB
    11. 4142
    Prev
    Next
    INDEX
    Explanations

    terms related to legal or official statements

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or statistics

    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
     weather
    -0.78
     tornado
    -0.73
     waterfall
    -0.72
     compass
    -0.69
     landscapes
    -0.69
     landsl
    -0.68
     afterlife
    -0.67
     transistor
    -0.66
     wardrobe
    -0.65
     hairst
    -0.64
    POSITIVE LOGITS
    SPONSORED
    1.65
    RELATED
    1.52
    According
    1.51
    ADVERTISEMENT
    1.49
    However
    1.47
    Specifically
    1.45
    Among
    1.44
    Advertisement
    1.43
    Such
    1.42
    Asked
    1.42
    Activations Density 0.372%

    No Known Activations