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. 16943
    Prev
    Next
    INDEX
    Explanations

    mentions of publishing activities and editions

    oai_token-act-pair · gpt-3.5-turbo

    references to recent publications or editions in a scholarly context

    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
     perceived
    -0.67
    entimes
    -0.65
     stunts
    -0.61
     prey
    -0.60
     partying
    -0.59
     brute
    -0.58
    ibling
    -0.57
     topp
    -0.57
     looming
    -0.57
     newcomers
    -0.56
    POSITIVE LOGITS
     Scrib
    0.74
     Archives
    0.72
     archives
    0.71
     archive
    0.70
    Production
    0.67
     Catal
    0.64
     auction
    0.62
     Archive
    0.62
    sonian
    0.62
    Edited
    0.61
    Activations Density 1.106%

    No Known Activations