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. 12643
    Prev
    Next
    INDEX
    Explanations

    keywords related to news headlines or current events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific election events and political figures

    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
     appre
    -0.74
     assum
    -0.70
     nav
    -0.69
     devs
    -0.68
     corpus
    -0.67
    Reviewer
    -0.66
    eday
    -0.65
     blat
    -0.64
     metab
    -0.63
    Lear
    -0.63
    POSITIVE LOGITS
    isconsin
    0.89
     Republican
    0.81
    psons
    0.73
     congressional
    0.72
    ptive
    0.71
    hillary
    0.71
    izza
    0.70
    PAC
    0.69
    esson
    0.69
    aska
    0.67
    Activations Density 0.077%

    No Known Activations