© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2191
    Prev
    Next
    INDEX
    Explanations

    numerical figures related to data or statistics

    oai_token-act-pair · gpt-3.5-turbo

    indicators of emotional distress or critical situations

    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
     therm
    -0.60
     supers
    -0.58
     sprung
    -0.57
     underdog
    -0.55
     paved
    -0.54
    ĸļ
    -0.54
     Consortium
    -0.54
     pard
    -0.54
     intro
    -0.53
     unequ
    -0.53
    POSITIVE LOGITS
    etc
    1.13
    Lastly
    1.09
    Finally
    1.06
     Lastly
    1.04
     etc
    1.01
    Additionally
    1.00
    Conclusion
    0.99
     Finally
    0.90
    Examples
    0.87
    Installation
    0.83
    Activations Density 0.196%

    No Known Activations