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. 6-RES-JB
    6. 8249
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a comparison or dual aspect

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction 'and' used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uel
    -0.76
    Ͻ
    -0.74
    eks
    -0.73
    ÃĽ
    -0.71
    IJ
    -0.71
    rance
    -0.71
    ³
    -0.70
    ivid
    -0.70
    oor
    -0.68
    iper
    -0.66
    POSITIVE LOGITS
     ours
    0.80
    nam
    0.71
     hers
    0.70
     sexes
    0.67
    chard
    0.66
     autobiography
    0.65
     theirs
    0.65
     CPI
    0.63
     nons
    0.62
     imperson
    0.61
    Activations Density 0.169%

    No Known Activations