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. 4-RES-JB
    6. 3901
    Prev
    Next
    INDEX
    Explanations

    references to software dependencies and installation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to software dependencies and requirements

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

    No Comments

    Negative Logits
    gm
    -0.87
    iday
    -0.83
    past
    -0.82
    tell
    -0.79
    upper
    -0.71
    ogether
    -0.70
    grim
    -0.70
    acha
    -0.69
    fm
    -0.69
    liam
    -0.68
    POSITIVE LOGITS
    encies
    1.29
     dependency
    1.09
     dependencies
    1.00
     injection
    0.95
    ency
    0.90
    lessly
    0.88
     injected
    0.73
     headache
    0.72
    ystem
    0.72
     patched
    0.71
    Activations Density 0.013%

    No Known Activations