© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 16716
    Prev
    Next
    INDEX
    Explanations

    symbols and foreign characters

    oai_token-act-pair · gpt-3.5-turbo

    the character 'Ľ'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comm
    -0.75
     cry
    -0.72
     catalogue
    -0.69
    isation
    -0.68
     Barnes
    -0.64
     Lag
    -0.63
     Class
    -0.62
     upon
    -0.61
     programme
    -0.61
     mix
    -0.61
    POSITIVE LOGITS
    Ľ
    4.64
    ļ
    2.06
    ľ
    1.91
    ij
    1.84
    Ļ
    1.78
    £
    1.75
    ĺ
    1.74
    ŀ
    1.74
    į
    1.73
    Ķ
    1.68
    Activations Density 0.014%

    No Known Activations