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. 5-RES-JB
    6. 20876
    Prev
    Next
    INDEX
    Explanations

    words related to laws, regulations, and official terms

    oai_token-act-pair · gpt-3.5-turbo

    the usage of significant pronouns and determiners in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     republic
    -0.64
     vigilance
    -0.64
    istration
    -0.63
     scanner
    -0.62
     reservations
    -0.61
    eatured
    -0.61
     democr
    -0.60
     Braz
    -0.59
     tourism
    -0.59
     reel
    -0.59
    POSITIVE LOGITS
     Own
    0.83
     Ones
    0.80
    ulhu
    0.79
    TPPStreamerBot
    0.76
     Started
    0.74
    Care
    0.73
    Maker
    0.71
     Himself
    0.71
     Points
    0.71
    wagen
    0.70
    Activations Density 0.591%

    No Known Activations