© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 17208
    Prev
    Next
    INDEX
    Explanations

    references related to Marvel's Spider-Man, particularly the character of Spider-Man and other characters in the Marvel Cinematic Universe

    oai_token-act-pair · gpt-3.5-turbo

    mentions of superhero movies and characters

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    minist
    -0.79
    zanne
    -0.75
    hower
    -0.74
    housing
    -0.73
    ickr
    -0.71
    vironment
    -0.70
    administ
    -0.69
    misc
    -0.69
    åĮ
    -0.67
    tera
    -0.65
    POSITIVE LOGITS
     Deadpool
    1.13
     superheroes
    1.04
     villains
    1.02
    canon
    0.99
     Marvel
    0.98
     villain
    0.98
     sequels
    0.96
     superhero
    0.93
     Wolverine
    0.93
     Spectre
    0.91
    Activations Density 0.342%

    No Known Activations