© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 16541
    Prev
    Next
    INDEX
    Explanations

    references related to the character "Peter Parker," also known as Spider-Man, including other characters and events associated with his storyline

    oai_token-act-pair · gpt-3.5-turbo

    references to specific characters in the superhero genre

    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
    hower
    -0.78
    ickr
    -0.74
    administ
    -0.69
    EPA
    -0.69
    minist
    -0.69
    TPPStreamerBot
    -0.67
    Traditional
    -0.67
    umen
    -0.66
    zanne
    -0.66
    toggle
    -0.65
    POSITIVE LOGITS
     Deadpool
    1.00
     villains
    0.97
    canon
    0.97
     villain
    0.95
     superheroes
    0.93
    buster
    0.92
     Joker
    0.92
     Daredevil
    0.91
     Wolverine
    0.89
     superhero
    0.89
    Activations Density 0.278%

    No Known Activations