© 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. 1-RES-JB
    11. 24325
    Prev
    Next
    INDEX
    Explanations

    the symbol "Ĺ"

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters with unique visual forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ukrainians
    -0.70
     trainers
    -0.69
     range
    -0.65
     prefrontal
    -0.65
     mids
    -0.64
     unidentified
    -0.63
    asonic
    -0.62
     achie
    -0.61
     partnerships
    -0.61
     fastest
    -0.60
    POSITIVE LOGITS
    Ĺ
    1.69
    ¤
    1.08
    é»Ĵ
    1.07
    µ
    1.07
    ®
    1.06
    ï¸ı
    1.05
    ĸ
    1.03
    ĵ
    1.02
    °
    1.01
    ¾
    1.00
    Activations Density 0.006%

    No Known Activations