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. 3-RES-JB
    6. 22065
    Prev
    Next
    INDEX
    Explanations

    keywords related to the software tool "Gradle."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Grad" and its variations, indicating a focus on gradation or levels of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ħĭ
    -0.75
     Shack
    -0.72
    OTA
    -0.65
    ItemTracker
    -0.62
     Role
    -0.61
    66666666
    -0.61
     wi
    -0.58
    \":
    -0.57
    ACA
    -0.57
     combined
    -0.56
    POSITIVE LOGITS
    uates
    1.59
    uated
    1.47
    uation
    1.41
    uations
    1.38
    uating
    1.33
    uate
    1.29
    ients
    1.13
    ient
    1.10
    iate
    0.97
    ually
    0.96
    Activations Density 0.011%

    No Known Activations