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. 21298
    Prev
    Next
    INDEX
    Explanations

    phrases and sentences where the concept of "taking advantage" is described

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to taking advantage of opportunities

    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
     Dough
    -0.57
    ŃĶ
    -0.56
     Chili
    -0.56
     brace
    -0.55
     chili
    -0.52
     fireball
    -0.52
     messenger
    -0.52
    liam
    -0.52
    odore
    -0.52
     submar
    -0.51
    POSITIVE LOGITS
     thereof
    1.26
     of
    1.08
    Of
    0.88
    oise
    0.80
    of
    0.78
     OF
    0.77
     Of
    0.76
    OF
    0.75
    fully
    0.71
    FUL
    0.71
    Activations Density 0.035%

    No Known Activations