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. 7-RES-JB
    6. 20502
    Prev
    Next
    INDEX
    Explanations

    words related to medical, technical, and geographical terms that contain the letter combination "h"

    oai_token-act-pair · gpt-3.5-turbo

    specific letters or letter combinations that indicate the presence of names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     underrated
    -0.67
     isol
    -0.64
    theless
    -0.61
     subordinate
    -0.61
     ACPI
    -0.60
     angular
    -0.59
    icut
    -0.59
     awaited
    -0.58
     Cornwall
    -0.58
     compliment
    -0.57
    POSITIVE LOGITS
    nikov
    0.90
    raper
    0.84
    Ó
    0.82
    midt
    0.80
    士
    0.78
    uler
    0.77
    olars
    0.77
    pling
    0.77
    attering
    0.77
    irts
    0.76
    Activations Density 0.241%

    No Known Activations