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. 616
    Prev
    Next
    INDEX
    Explanations

    names of specific entities such as cities, places, people and categories

    oai_token-act-pair · gpt-3.5-turbo

    key entities and concepts related to legal cases and their implications

    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
    joice
    -0.73
    dx
    -0.69
    CAST
    -0.68
    interrupted
    -0.68
    thumbnails
    -0.67
     Pry
    -0.67
     condem
    -0.64
    wards
    -0.64
    rys
    -0.63
    repeat
    -0.63
    POSITIVE LOGITS
    é¾įå¥ij士
    0.78
     alone
    0.75
    ieri
    0.72
    eto
    0.68
    ativity
    0.67
     Cooke
    0.66
    igmat
    0.66
    ema
    0.61
    ISO
    0.61
     Ronaldo
    0.61
    Activations Density 0.200%

    No Known Activations