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. 2467
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person's name, "Tr" along with a varying sequence of numbers after it

    oai_token-act-pair · gpt-3.5-turbo

    the term "Tr" followed by a number, likely referring to a specific topic or identifier in a technical or academic 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
    ãģ®éŃĶ
    -0.79
    WARE
    -0.76
    ELS
    -0.74
    furt
    -0.73
    lihood
    -0.71
    manship
    -0.71
     arts
    -0.71
    âĸ¬âĸ¬
    -0.70
    MENTS
    -0.67
    eers
    -0.67
    POSITIVE LOGITS
    ainer
    1.22
    acer
    1.16
    unn
    1.09
    ained
    1.08
    itton
    1.08
    ilateral
    1.08
    unk
    1.06
    umps
    1.05
    istan
    1.04
    acing
    1.04
    Activations Density 0.013%

    No Known Activations