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. 6293
    Prev
    Next
    INDEX
    Explanations

    keywords related to tasks or actions that require assistance or guidance

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express necessity or requirement

    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
     Democr
    -0.76
    cow
    -0.62
     Brewers
    -0.61
    pee
    -0.60
     Pill
    -0.59
    ihu
    -0.58
     Sturgeon
    -0.58
     Bad
    -0.57
    cession
    -0.57
    cheat
    -0.57
    POSITIVE LOGITS
    lessly
    1.25
    ache
    0.88
    igslist
    0.72
    aches
    0.70
    n
    0.68
    LES
    0.68
     assistance
    0.67
    ancies
    0.67
    nces
    0.64
     sust
    0.64
    Activations Density 0.062%

    No Known Activations