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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 21773
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "comics"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of comics and comic-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ntil
    -0.76
    holm
    -0.70
    beam
    -0.67
    strom
    -0.67
    ĪĴ
    -0.66
    wreck
    -0.66
     rusty
    -0.65
    ney
    -0.64
    idate
    -0.64
    tenance
    -0.64
    POSITIVE LOGITS
     Comics
    1.09
     comics
    0.99
     superheroes
    0.83
     superhero
    0.82
     comic
    0.77
     Presents
    0.77
    ento
    0.75
     publishers
    0.73
     sans
    0.73
     shorts
    0.73
    Activations Density 0.012%

    No Known Activations