© 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. 1-RES-JB
    11. 3945
    Prev
    Next
    INDEX
    Explanations

    a specific symbol 'Ļ' appearing in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or symbol

    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
    yip
    -0.64
    anium
    -0.64
     promoters
    -0.59
    omething
    -0.59
     loopholes
    -0.58
     hindsight
    -0.58
     sophistication
    -0.57
     Gutenberg
    -0.57
    eon
    -0.57
     Raleigh
    -0.56
    POSITIVE LOGITS
    Ļ
    1.10
    taboola
    0.97
    女
    0.95
    ļ
    0.88
    º
    0.88
    ķ
    0.86
    ħ
    0.86
    £
    0.85
    ı
    0.85
    Ľ
    0.81
    Activations Density 0.288%

    No Known Activations