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. 4002
    Prev
    Next
    INDEX
    Explanations

    phrases related to urgent action or emergency situations

    oai_token-act-pair · gpt-3.5-turbo

    references to urgency or haste

    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
     princip
    -0.66
    oci
    -0.63
    opher
    -0.63
     domin
    -0.62
    igen
    -0.61
     Match
    -0.61
    uit
    -0.60
    oln
    -0.59
     Influence
    -0.59
    Gener
    -0.59
    POSITIVE LOGITS
     rushed
    3.71
     hurried
    2.08
     rush
    2.04
     rushes
    1.98
     rushing
    1.75
     hastily
    1.52
     raced
    1.48
     haste
    1.33
    rush
    1.29
     sped
    1.29
    Activations Density 0.028%

    No Known Activations