© 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. 752
    Prev
    Next
    INDEX
    Explanations

    numerical and special characters that may form a pattern or code

    oai_token-act-pair · gpt-3.5-turbo

    special characters and non-standard text elements, possibly indicating encoded or corrupted data

    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
    eways
    -0.60
    merce
    -0.60
     Topics
    -0.55
     wors
    -0.54
     sidebar
    -0.54
    Graphics
    -0.53
    ciples
    -0.52
     intrins
    -0.52
     Stud
    -0.52
    nces
    -0.51
    POSITIVE LOGITS
    ´
    0.86
    и
    0.84
    ľ
    0.82
    Ħ
    0.81
    Ń·
    0.79
    ħ
    0.78
    о
    0.76
    Ķ
    0.75
    ¬
    0.73
    ł
    0.73
    Activations Density 0.047%

    No Known Activations