Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 13041
    Prev
    Next
    INDEX
    Explanations

    a pattern related to various characters and symbols, potentially indicating a specific coding language or encryption method

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and references to mathematical symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phrine
    -0.74
    ĸļ
    -0.68
    atche
    -0.65
    ĪĴ
    -0.64
     parchment
    -0.60
     hole
    -0.59
     solicit
    -0.59
     motel
    -0.59
    ogyn
    -0.58
    hole
    -0.58
    POSITIVE LOGITS
    luster
    0.83
    ij士
    0.73
    gage
    0.70
    idated
    0.70
    atoes
    0.69
    ilot
    0.69
    rations
    0.67
    rano
    0.67
    hesda
    0.67
    ãĤ¼ãĤ¦ãĤ¹
    0.67
    Activations Density 0.353%

    No Known Activations