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. 2721
    Prev
    Next
    INDEX
    Explanations

    topics or subjects being discussed or focused on in text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "topic."

    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
     Zimmer
    -0.70
    igned
    -0.70
    ignt
    -0.69
    hovah
    -0.66
    inyl
    -0.65
    leeve
    -0.65
    ardo
    -0.64
    ramid
    -0.63
    omp
    -0.62
    ATES
    -0.61
    POSITIVE LOGITS
     topics
    0.95
    Topic
    0.92
    matter
    0.91
     topic
    0.88
    topic
    0.87
     Topics
    0.83
    TextColor
    0.80
    Topics
    0.78
    userc
    0.78
    forum
    0.75
    Activations Density 0.022%

    No Known Activations