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. 9175
    Prev
    Next
    INDEX
    Explanations

    references to pacifiers or uses of pacifier as a metaphor

    oai_token-act-pair · gpt-3.5-turbo

    references to pacifiers or items that soothe and calm, especially in a caregiving context

    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
    âĵĺ
    -0.84
    âĢ¢âĢ¢
    -0.82
     Likes
    -0.71
     ABE
    -0.71
    assetsadobe
    -0.71
     Marketable
    -0.69
    isSpecialOrderable
    -0.68
    IELD
    -0.68
    çīĪ
    -0.66
     Rates
    -0.64
    POSITIVE LOGITS
     pac
    1.41
    ific
    1.16
    pac
    0.97
    Pac
    0.90
    emaker
    0.87
    rome
    0.86
    wu
    0.85
    ervative
    0.83
    rop
    0.82
    nam
    0.81
    Activations Density 0.004%

    No Known Activations