Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 17122
    Prev
    Next
    INDEX
    Explanations

    names of individuals or public figures

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals in Korean culture and politics

    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
     cort
    -0.72
    20439
    -0.71
     ERROR
    -0.69
    ãĤ©
    -0.68
     HELL
    -0.68
     miscarriage
    -0.68
     COVER
    -0.67
     Alleg
    -0.67
     barn
    -0.66
     ORDER
    -0.65
    POSITIVE LOGITS
    wei
    1.23
    jin
    1.20
    jri
    1.08
     Kong
    1.08
    qi
    1.06
    jiang
    1.05
     Guang
    1.05
     Cheng
    1.03
    Hong
    1.02
     Jiang
    1.01
    Activations Density 0.181%

    No Known Activations