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. 13776
    Prev
    Next
    INDEX
    Explanations

    references to the company "Shell" and related topics such as oil, offshore drilling, and environmental impact

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the company "Shell"

    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
    ————————————————
    -0.80
    Interstitial
    -0.76
    âĸĪâĸĪ
    -0.72
    é¾įå
    -0.71
     Scand
    -0.70
     ILCS
    -0.70
    ————————
    -0.67
    upon
    -0.66
    favorite
    -0.64
     Clare
    -0.62
    POSITIVE LOGITS
     Shell
    1.17
    shell
    1.12
    Shell
    0.99
    shock
    0.97
     shells
    0.95
    fish
    0.86
     shell
    0.82
    wagen
    0.80
    helm
    0.78
    heed
    0.76
    Activations Density 0.005%

    No Known Activations