© 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. 10-RES-JB
    11. 6691
    Prev
    Next
    INDEX
    Explanations

    mentions of zombies

    oai_token-act-pair · gpt-3.5-turbo

    references to zombies and related themes in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ional
    -0.89
    cipled
    -0.81
    ours
    -0.79
    ª
    -0.79
    İ
    -0.76
    tons
    -0.76
    ¿½
    -0.75
    alty
    -0.74
    ¡
    -0.74
    romy
    -0.74
    POSITIVE LOGITS
     apocalypse
    1.31
     Apocalypse
    1.26
     horde
    1.04
     zombie
    1.02
     plague
    1.00
     hordes
    0.98
     zombies
    0.96
     squid
    0.92
     Slayer
    0.92
     outbreak
    0.92
    Activations Density 0.070%

    No Known Activations