© 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. 24076
    Prev
    Next
    INDEX
    Explanations

    terms that are encoded with special characters

    oai_token-act-pair · gpt-3.5-turbo

    repeated characters in words

    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
     incorpor
    -0.85
     contrace
    -0.81
     secretaries
    -0.79
     pickups
    -0.78
     fortun
    -0.76
     warr
    -0.75
     manif
    -0.74
     mathemat
    -0.74
     unborn
    -0.72
     accur
    -0.71
    POSITIVE LOGITS
    ï¸ı
    1.25
    ï¸
    0.98
    VERTISEMENT
    0.89
     Originally
    0.86
    ¯
    0.85
     Edited
    0.84
     âĢº
    0.84
    âĻ
    0.80
     Previous
    0.79
    âĶĢâĶĢ
    0.79
    Activations Density 0.127%

    No Known Activations