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. 7-RES-JB
    6. 15594
    Prev
    Next
    INDEX
    Explanations

    keywords related to instructions and methods, such as "Supports," "Allows," "Makes," "Runs," "Uses," "Includes," and "Requires."

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating actions, particularly in the context of support or assistance

    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
    eur
    -0.74
    lord
    -0.73
    phant
    -0.66
    gan
    -0.65
    lier
    -0.65
     conqu
    -0.62
     witnesses
    -0.61
    aneously
    -0.60
    rone
    -0.59
    bomb
    -0.59
    POSITIVE LOGITS
    hift
    1.26
    pace
    1.24
    paces
    1.10
    omething
    1.10
    ource
    1.07
    ometimes
    1.01
    creen
    1.00
    heet
    1.00
    cript
    0.94
    ynthesis
    0.93
    Activations Density 0.234%

    No Known Activations