© 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. 0-RES-JB
    11. 7528
    Prev
    Next
    INDEX
    Explanations

    words in a specific foreign language

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols typically found in proprietary or formatted content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mode
    -0.73
     response
    -0.67
     mash
    -0.64
     Hunts
    -0.60
     takedown
    -0.60
     strategy
    -0.60
     Madison
    -0.60
     timetable
    -0.60
     pose
    -0.60
     tactic
    -0.60
    POSITIVE LOGITS
    ij
    4.47
    IJ
    2.07
    Ľ
    1.88
    İ
    1.86
    Ķ
    1.85
    į
    1.84
    Ĵ
    1.83
    ı
    1.79
    ĺ
    1.73
    Ĺ
    1.72
    Activations Density 0.008%

    No Known Activations