Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 736
    Prev
    Next
    INDEX
    Explanations

    instances of the word "inquiry"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "inquiry" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    birth
    -0.76
    perm
    -0.67
    Corn
    -0.67
    Lago
    -0.65
    jc
    -0.65
    hoff
    -0.62
    KI
    -0.62
    absolute
    -0.60
    Fa
    -0.60
    Aid
    -0.60
    POSITIVE LOGITS
     inquiry
    1.10
     probing
    1.05
     Inquiry
    1.02
     hearings
    0.93
    naires
    0.89
    izabeth
    0.84
     inquiries
    0.81
     investigates
    0.81
    iry
    0.75
    isition
    0.74
    Activations Density 0.023%

    No Known Activations