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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 20373
    Prev
    Next
    INDEX
    Explanations

    words related to zombies

    oai_token-act-pair · gpt-3.5-turbo

    references to zombies and related themes in media

    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
    Ctrl
    -0.80
    ugu
    -0.76
    ours
    -0.74
    ickr
    -0.74
    ional
    -0.73
    å§«
    -0.72
    stro
    -0.72
    sers
    -0.71
    obar
    -0.71
    inates
    -0.70
    POSITIVE LOGITS
     apocalypse
    1.16
     zombie
    1.08
    ombies
    1.07
     Apocalypse
    1.02
     zombies
    0.97
     horde
    0.96
    ombie
    0.93
     Zombie
    0.87
     outbreak
    0.85
     lair
    0.83
    Activations Density 0.011%

    No Known Activations