© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16700
    Prev
    Next
    INDEX
    Explanations

    uncommon symbols and special characters

    oai_token-act-pair · gpt-3.5-turbo

    repeated characters and special 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 @ 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
     vividly
    -0.69
     Forever
    -0.64
     1937
    -0.63
     sacrific
    -0.63
     Sammy
    -0.63
     once
    -0.61
     Drawn
    -0.61
     Till
    -0.61
     Reyn
    -0.61
     Jinn
    -0.61
    POSITIVE LOGITS
    ï¸ı
    0.96
    mental
    0.94
    tal
    0.93
    sic
    0.90
    20439
    0.87
    Reviewer
    0.86
    cause
    0.86
    cation
    0.85
    economic
    0.85
    cre
    0.84
    Activations Density 0.179%

    No Known Activations