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. 2-RES-JB
    6. 1136
    Prev
    Next
    INDEX
    Explanations

    instances of the term "Sec" followed by a single-digit number

    oai_token-act-pair · gpt-3.5-turbo

    references to "Sec," which appears to denote a particular section or title in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.80
     Burnett
    -0.77
    lihood
    -0.74
     Warcraft
    -0.74
    ãĥ£
    -0.71
    çİĭ
    -0.70
    FORE
    -0.69
     GOODMAN
    -0.68
    ãĥĥãĤ¯
    -0.66
     Silk
    -0.65
    POSITIVE LOGITS
    Sec
    1.05
    unia
    1.02
    ular
    0.95
    recy
    0.94
    rets
    0.94
    ession
    0.92
    unda
    0.91
    aucus
    0.91
    ularity
    0.83
    urities
    0.83
    Activations Density 0.005%

    No Known Activations