© 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. 10-RES-JB
    11. 11559
    Prev
    Next
    INDEX
    Explanations

    non-English characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters or non-standard symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     demos
    -0.87
     factions
    -0.74
     neighb
    -0.74
     unpop
    -0.74
     challeng
    -0.73
     grips
    -0.73
     blacklist
    -0.71
     wrinkles
    -0.71
    okin
    -0.71
     piracy
    -0.70
    POSITIVE LOGITS
    à¥
    2.14
    à¤
    2.14
    ा
    1.98
     à¤
    1.78
    ×Ļ×
    1.49
    ×Ķ
    1.46
    ×ķ
    1.46
    ×
    1.43
    ר
    1.41
    ×Ļ
    1.39
    Activations Density 0.007%

    No Known Activations