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. 23539
    Prev
    Next
    INDEX
    Explanations

    code-related terms and grammar symbols such as parentheses, brackets, and equals signs

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements and options related to choice

    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
     Lia
    -0.52
     Kah
    -0.52
    atorium
    -0.49
    mpeg
    -0.49
     Marlins
    -0.45
     Ven
    -0.45
     Sanctuary
    -0.45
     Tours
    -0.45
    iage
    -0.44
     Field
    -0.44
    POSITIVE LOGITS
    depending
    0.78
    ãĤ´ãĥ³
    0.61
     respectively
    0.58
     undermin
    0.56
     charact
    0.55
     ancest
    0.54
    ONSORED
    0.54
     explan
    0.54
    é¾įåĸļ士
    0.54
     challeng
    0.53
    Activations Density 1.799%

    No Known Activations