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

    Neuronpedia

    APICircuit 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. 11-RES-JB
    6. 15374
    Prev
    Next
    INDEX
    Explanations

    mentions of characters and elements related to the Batman franchise

    oai_token-act-pair · gpt-3.5-turbo

    references to Batman and Superman in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sweet
    -0.95
    ateur
    -0.85
    bush
    -0.79
    iment
    -0.76
    ateurs
    -0.74
    grain
    -0.72
    dn
    -0.72
     Eston
    -0.71
    chell
    -0.71
    atories
    -0.70
    POSITIVE LOGITS
     Arkham
    1.34
     Begins
    1.33
     Returns
    1.24
     Origins
    1.16
     Comics
    1.10
     Forever
    1.08
     comics
    1.04
     Unch
    1.00
     villains
    0.99
     Rebirth
    0.99
    Activations Density 0.122%

    No Known Activations