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. 8-RES-JB
    6. 5395
    Prev
    Next
    INDEX
    Explanations

    words related to various actions and activities such as subsidizing, compressing, stretching, crocheting, screening, chopping, downloading, etc

    oai_token-act-pair · gpt-3.5-turbo

    verbs that describe actions related to managing and organizing tasks or projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ings
    -0.85
    yah
    -0.79
    tis
    -0.77
    abet
    -0.77
    eda
    -0.75
    arta
    -0.73
    é¾įåĸļ士
    -0.72
    held
    -0.72
    stones
    -0.70
    weather
    -0.70
    POSITIVE LOGITS
     Eag
    0.78
    nesday
    0.64
     hemor
    0.63
     herself
    0.63
     himself
    0.62
     myself
    0.61
    uled
    0.60
     extensively
    0.60
     Beaut
    0.60
     UCH
    0.59
    Activations Density 0.546%

    No Known Activations