© 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. 8-RES-JB
    6. 7187
    Prev
    Next
    INDEX
    Explanations

    strings of characters similar to computer code or data types

    oai_token-act-pair · gpt-3.5-turbo

    the character "ľ" which appears in various contexts throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mirage
    -0.74
     Nau
    -0.73
     condem
    -0.72
     Polk
    -0.70
     Palm
    -0.67
     delegation
    -0.65
     Seym
    -0.64
     Patriarch
    -0.64
     clitor
    -0.64
     ways
    -0.64
    POSITIVE LOGITS
    ï¸ı
    1.30
    _>
    1.01
    ternity
    0.95
    §
    0.95
    $
    0.92
    cffffcc
    0.90
    âĶĢâĶĢ
    0.90
    wow
    0.87
    xxx
    0.87
    Ïī
    0.86
    Activations Density 0.170%

    No Known Activations