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. 0-RES-JB
    6. 14078
    Prev
    Next
    INDEX
    Explanations

    words related to emergency situations or alarms

    oai_token-act-pair · gpt-3.5-turbo

    references to sirens and expressions of joy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Layer
    -0.74
    gender
    -0.71
    tie
    -0.67
     Fur
    -0.67
     Phi
    -0.65
     âĨij
    -0.64
    Layer
    -0.61
    orable
    -0.61
     ATF
    -0.61
     commission
    -0.60
    POSITIVE LOGITS
    iren
    1.92
    joy
    1.60
     richer
    1.59
    irens
    1.53
    akia
    1.44
    aye
    1.13
     SHARES
    1.11
     celebrations
    1.09
     poorer
    1.07
     wealthier
    0.98
    Activations Density 0.038%

    No Known Activations