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. 10739
    Prev
    Next
    INDEX
    Explanations

    information related to astronomical objects, particularly the Milky Way galaxy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the Milky Way galaxy and specific references to characters and elements from the Mortal Kombat franchise

    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
    ually
    -0.78
    è¯
    -0.75
    umat
    -0.72
    ARDIS
    -0.69
    RAFT
    -0.68
     Gott
    -0.66
    ãĥ¼ãĥ
    -0.64
    agall
    -0.63
     Warner
    -0.63
    izations
    -0.62
    POSITIVE LOGITS
    sie
    0.85
    ramid
    0.83
    doms
    0.80
     lapt
    0.78
    olicy
    0.77
    iries
    0.76
    irements
    0.75
    zie
    0.74
    eon
    0.73
    arij
    0.73
    Activations Density 0.048%

    No Known Activations