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. 24254
    Prev
    Next
    INDEX
    Explanations

    the word "profound" in the text

    oai_token-act-pair · gpt-3.5-turbo

    the word "profound" and its context related to significant effects or implications

    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
    ©¶æ
    -0.94
    phis
    -0.84
    CDC
    -0.76
    MIC
    -0.74
     Garrison
    -0.69
    ope
    -0.66
    matched
    -0.65
    llah
    -0.65
    paces
    -0.65
    hops
    -0.65
    POSITIVE LOGITS
    ly
    0.82
    est
    0.79
    ness
    0.77
     impact
    0.76
     philosophical
    0.76
     profound
    0.75
     fascination
    0.74
     significance
    0.74
     sadness
    0.74
     insight
    0.73
    Activations Density 0.007%

    No Known Activations