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. 10-RES-JB
    6. 14634
    Prev
    Next
    INDEX
    Explanations

    words related to transportation and travel

    oai_token-act-pair · gpt-3.5-turbo

    instances of text related to specific actions or transitions, particularly those with varying conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĥª
    -0.84
    CLUS
    -0.75
    é¾
    -0.73
    abouts
    -0.72
    è¦ļéĨĴ
    -0.67
    ":"/
    -0.66
    ãĥ¼ãĥ
    -0.64
    etheless
    -0.62
    ront
    -0.62
    rio
    -0.61
    POSITIVE LOGITS
     etc
    1.43
     or
    1.41
     nor
    1.10
     whereas
    1.04
    etc
    0.96
     versus
    0.91
     but
    0.89
     Or
    0.86
     respectively
    0.85
     thereby
    0.82
    Activations Density 0.421%

    No Known Activations