© 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. 11-RES-JB
    11. 23730
    Prev
    Next
    INDEX
    Explanations

    references to the TV show "The Walking Dead" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    details about characters and plot developments in "The Walking Dead."

    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
    Saudi
    -1.13
    ÄŁ
    -1.10
     FISA
    -0.99
     Saudi
    -0.95
    oÄŁ
    -0.94
     FAA
    -0.94
     Saudis
    -0.93
     Malays
    -0.92
    £ı
    -0.90
     Riyadh
    -0.89
    POSITIVE LOGITS
     zombie
    1.99
     zombies
    1.95
     Zombie
    1.87
     Zombies
    1.79
     AMC
    1.69
     Romero
    1.61
     Walking
    1.61
     undead
    1.53
     Dead
    1.41
    ombie
    1.29
    Activations Density 0.259%

    No Known Activations