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. 1787
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Kat" with various additional characters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific person named Kat

    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
    cffff
    -0.85
    CLASSIFIED
    -0.80
    LEASE
    -0.79
    uploads
    -0.72
     confir
    -0.71
    prise
    -0.69
     contraceptives
    -0.67
    lict
    -0.66
     margins
    -0.65
    interstitial
    -0.64
    POSITIVE LOGITS
    anas
    1.17
     Kat
    1.03
    usha
    0.98
    kat
    0.96
    apesh
    0.89
    ney
    0.88
    Kat
    0.87
    zen
    0.85
    oton
    0.84
    ana
    0.84
    Activations Density 0.012%

    No Known Activations