© 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. 6-RES-JB
    11. 13525
    Prev
    Next
    INDEX
    Explanations

    specific special characters in text, especially with numbers appended

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities with the symbol "Ļ."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mathemat
    -0.85
     contrace
    -0.84
     disadvant
    -0.79
     Palestin
    -0.79
     Soviets
    -0.75
     vulner
    -0.74
     fortun
    -0.73
     welf
    -0.72
     traffickers
    -0.72
     misunder
    -0.71
    POSITIVE LOGITS
    ï¸ı
    1.14
    tre
    0.90
    ï¸
    0.89
    ski
    0.88
    lime
    0.84
    eric
    0.83
    ship
    0.82
    CEO
    0.80
    pine
    0.75
    better
    0.74
    Activations Density 0.307%

    No Known Activations