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. 6-RES-JB
    6. 4862
    Prev
    Next
    INDEX
    Explanations

    references to specific technology products, particularly smartphones

    oai_token-act-pair · gpt-3.5-turbo

    references to specific product names and brands, particularly mobile phones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ning
    -0.73
    ned
    -0.73
    ãĤ§
    -0.72
     Freddie
    -0.70
    idation
    -0.68
     Flavoring
    -0.66
    llah
    -0.65
     disinfect
    -0.65
    nikov
    -0.65
    iyah
    -0.64
    POSITIVE LOGITS
    ©¶æ¥µ
    0.92
    ota
    0.89
    Į
    0.88
    yg
    0.83
    ı
    0.81
    itsu
    0.80
    rell
    0.79
    zeb
    0.79
    unes
    0.78
    ī
    0.77
    Activations Density 0.034%

    No Known Activations