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. 10384
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Buddy"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Buddy" and its variations in the context of transactions and individuals

    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
    ined
    -0.83
    abad
    -0.83
    ariat
    -0.82
    ured
    -0.80
    urers
    -0.79
    apers
    -0.79
    ors
    -0.79
    inery
    -0.78
    orate
    -0.77
    orescence
    -0.76
    POSITIVE LOGITS
     Nico
    0.82
     Miles
    0.79
     Wynne
    0.77
    onym
    0.76
     Vaughn
    0.73
    metry
    0.72
     Nolan
    0.72
    hiro
    0.71
     Hanna
    0.71
    cedes
    0.70
    Activations Density 0.022%

    No Known Activations