© 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. 1278
    Prev
    Next
    INDEX
    Explanations

    programming code and error messages

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and warnings related to programming errors and other issues

    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
    omething
    -0.69
     oun
    -0.67
    ijing
    -0.66
     helicop
    -0.61
    vernment
    -0.60
    é¾į
    -0.58
     carbohyd
    -0.57
     bom
    -0.57
     Lans
    -0.56
    aware
    -0.56
    POSITIVE LOGITS
    --------------------------------------------------------
    0.76
    %%%%
    0.68
    Merit
    0.66
     CONTIN
    0.66
    âĶĢâĶĢâĶĢâĶĢ
    0.62
    Conclusion
    0.61
    CONCLUS
    0.59
    ======
    0.58
     FINAL
    0.57
    "]=>
    0.57
    Activations Density 0.268%

    No Known Activations