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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 6663
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters and government activities

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols that may indicate a specific format or coding language within 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
     charm
    -0.70
     scatter
    -0.69
     Nemesis
    -0.67
     scattering
    -0.66
     cyan
    -0.66
     lovers
    -0.65
     Nept
    -0.65
     nod
    -0.62
     Kirin
    -0.62
     GF
    -0.62
    POSITIVE LOGITS
    ¹
    1.02
    º
    1.00
    £
    0.97
    Jackson
    0.90
    Į
    0.88
    tesy
    0.87
    Ĵ
    0.87
    ISIS
    0.86
    ¸
    0.86
    ı
    0.86
    Activations Density 0.397%

    No Known Activations