Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 15915
    Prev
    Next
    INDEX
    Explanations

    the character 'Ļ' and 'Ċ' followed by a number 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    the character reference or symbol 'Ļ' in 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
     Folk
    -0.67
     Wilmington
    -0.64
     advisers
    -0.64
     exposures
    -0.63
     Antar
    -0.63
     logger
    -0.62
     township
    -0.62
     recycling
    -0.61
     landfill
    -0.61
     kicker
    -0.61
    POSITIVE LOGITS
    ï¸ı
    1.46
    âĻ
    0.99
    âĶĢâĶĢâĶĢâĶĢ
    0.86
    Balt
    0.86
    ï¸
    0.85
    _>
    0.85
    女
    0.85
    âĹ
    0.84
    âĤ¬
    0.84
    £
    0.81
    Activations Density 0.318%

    No Known Activations