© 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. 13791
    Prev
    Next
    INDEX
    Explanations

    a specific character encoding or language pattern

    oai_token-act-pair · gpt-3.5-turbo

    characters from non-Latin scripts or possibly non-readable 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
     board
    -0.81
     merch
    -0.69
     cheer
    -0.68
     panels
    -0.68
     Bree
    -0.67
     cooler
    -0.67
     apparel
    -0.66
     Franch
    -0.66
     favor
    -0.64
     opportunity
    -0.63
    POSITIVE LOGITS
    ²
    1.84
    º
    1.78
    ½
    1.72
    ´
    1.71
    ±
    1.69
    ¾
    1.69
    ¸
    1.68
    ³
    1.66
    Ń
    1.62
    °
    1.55
    Activations Density 0.024%

    No Known Activations