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. 17421
    Prev
    Next
    INDEX
    Explanations

    instances of the word "inquiry"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of inquiries or investigations

    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
     Kinnikuman
    -0.66
     Extrem
    -0.63
     Defensive
    -0.62
    perm
    -0.58
     Kers
    -0.58
    Hero
    -0.57
     dotted
    -0.56
    shared
    -0.56
    ected
    -0.56
     MIDI
    -0.55
    POSITIVE LOGITS
     inquiry
    1.35
     Inquiry
    1.24
     inquiries
    1.04
     enqu
    1.02
     inquire
    0.98
    izabeth
    0.98
     probing
    0.94
    naires
    0.87
     seekers
    0.87
     hearings
    0.85
    Activations Density 0.009%

    No Known Activations