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. 7339
    Prev
    Next
    INDEX
    Explanations

    the name "Thomas" with varying confidence levels

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Thomas."

    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
    fecture
    -0.89
    yip
    -0.85
    eer
    -0.81
    ebus
    -0.78
    ebook
    -0.77
    yrinth
    -0.77
    sites
    -0.76
    places
    -0.76
    ptions
    -0.76
    Ĥª
    -0.73
    POSITIVE LOGITS
     Jefferson
    0.89
     Browne
    0.89
     Aqu
    0.89
     Hardy
    0.83
     Mulcair
    0.80
     Crom
    0.75
     Beach
    0.72
     Hood
    0.70
     Fors
    0.69
     Edison
    0.69
    Activations Density 0.016%

    No Known Activations