© 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. 4371
    Prev
    Next
    INDEX
    Explanations

    specific symbols or characters

    oai_token-act-pair · gpt-3.5-turbo

    unique characters or symbols in the text

    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
     glim
    -0.79
     itiner
    -0.75
    uggest
    -0.71
     confir
    -0.69
     conduc
    -0.64
     arsenic
    -0.64
     satell
    -0.63
    ijah
    -0.61
     incorpor
    -0.61
    iage
    -0.60
    POSITIVE LOGITS
    %"
    0.99
    ¯
    0.91
    ï¸ı
    0.90
    âĢ
    0.80
    âĶĢâĶĢâĶĢâĶĢ
    0.79
    """
    0.78
    >>>
    0.75
    www
    0.75
    âĶĢâĶĢ
    0.74
    Ð
    0.73
    Activations Density 0.124%

    No Known Activations