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. 915
    Prev
    Next
    INDEX
    Explanations

    verbs related to encountering a challenge or obstacle

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "faced" in various contexts, indicating challenges or obstacles encountered

    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
    optional
    -0.70
    orate
    -0.63
    rats
    -0.61
    ext
    -0.59
     Optional
    -0.57
    ership
    -0.57
     Wonderful
    -0.57
     refinement
    -0.57
     Definitive
    -0.56
    OR
    -0.56
    POSITIVE LOGITS
     faced
    3.69
     facing
    2.11
     confronted
    2.02
     faces
    1.94
     face
    1.88
     encountered
    1.55
    faced
    1.55
     endured
    1.41
     posed
    1.36
     confronting
    1.31
    Activations Density 0.011%

    No Known Activations