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. 1-RES-JB
    6. 8406
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to highways or roads

    oai_token-act-pair · gpt-3.5-turbo

    mentions of roadways and pathways

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itu
    -0.79
    uster
    -0.68
    ums
    -0.68
    rum
    -0.66
    umb
    -0.65
    hemat
    -0.65
     Eliot
    -0.64
     Ludwig
    -0.62
    agged
    -0.61
     Ars
    -0.60
    POSITIVE LOGITS
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.94
    tainment
    0.92
    eway
    0.92
    ahime
    0.89
     embr
    0.88
    terness
    0.87
    bos
    0.87
    ãĥį
    0.86
    ãĤ©
    0.85
    ãĥ¥
    0.83
    Activations Density 0.012%

    No Known Activations