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. 3543
    Prev
    Next
    INDEX
    Explanations

    words related to harvesting or obtaining something, such as reaping or reaping

    oai_token-act-pair · gpt-3.5-turbo

    words with suffixes related to modification or change

    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
    mson
    -0.78
     substituted
    -0.66
    acca
    -0.64
     deported
    -0.62
     substit
    -0.61
     Bangalore
    -0.61
     Flint
    -0.60
     Gray
    -0.60
     Delete
    -0.59
    Chelsea
    -0.58
    POSITIVE LOGITS
    vern
    0.76
    prises
    0.71
    igion
    0.68
    kefeller
    0.68
    DOM
    0.68
    uin
    0.67
    phony
    0.66
    quit
    0.65
    aliation
    0.65
    arious
    0.64
    Activations Density 0.088%

    No Known Activations