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. 18683
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "know"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "I don't know."

    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
    phrine
    -0.83
    isco
    -0.81
    attery
    -0.77
     sidx
    -0.77
    otom
    -0.73
    ItemTracker
    -0.73
    gencies
    -0.72
    conservancy
    -0.72
    coni
    -0.71
    gdala
    -0.70
    POSITIVE LOGITS
     exactly
    0.81
    lege
    0.81
     how
    0.79
    ledged
    0.75
     anymore
    0.72
     anything
    0.68
    hin
    0.67
     ABOUT
    0.66
     why
    0.66
     whether
    0.66
    Activations Density 0.029%

    No Known Activations