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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 8661
    Prev
    Next
    INDEX
    Explanations

    mentions of the Marvel universe or Marvel-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the Marvel franchise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    choes
    -0.73
    orescence
    -0.72
    gger
    -0.69
    skirts
    -0.68
    orative
    -0.67
    perture
    -0.67
    cki
    -0.67
    PER
    -0.66
    thia
    -0.66
    cipline
    -0.66
    POSITIVE LOGITS
    Marvel
    1.05
     Comics
    1.01
     Marvel
    0.99
     Avengers
    0.89
    ous
    0.87
     superheroes
    0.86
     Mansion
    0.84
     Studios
    0.82
     superhero
    0.80
     Cinem
    0.78
    Activations Density 0.010%

    No Known Activations