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. 2466
    Prev
    Next
    INDEX
    Explanations

    programming-related commands and instructions

    oai_token-act-pair · gpt-3.5-turbo

    user interface elements and instructions related to software navigation

    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
    wives
    -0.73
    ergy
    -0.72
    nell
    -0.71
    idious
    -0.68
     dope
    -0.67
    blogspot
    -0.67
    atti
    -0.66
    iaries
    -0.65
     paternity
    -0.65
    utic
    -0.65
    POSITIVE LOGITS
     icon
    0.89
     Settings
    0.87
     Keyboard
    0.87
     Preferences
    0.87
     Config
    0.86
    Config
    0.84
     Exit
    0.80
     Login
    0.79
     Scroll
    0.79
     clipboard
    0.78
    Activations Density 0.290%

    No Known Activations