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. 2549
    Prev
    Next
    INDEX
    Explanations

    phrases related to establishing or initiating something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "set up."

    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
    obi
    -0.77
    Brow
    -0.71
    axe
    -0.64
    onso
    -0.64
    doi
    -0.64
    cold
    -0.62
    âĨij
    -0.62
    BL
    -0.61
    hound
    -0.61
    catentry
    -0.60
    POSITIVE LOGITS
     tents
    0.82
    olicy
    0.75
     partitions
    0.72
     rapport
    0.71
    dule
    0.71
     foundations
    0.70
     camp
    0.70
     shop
    0.69
     banners
    0.69
    roups
    0.67
    Activations Density 0.029%

    No Known Activations