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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-RES-JB
    6. 21823
    Prev
    Next
    INDEX
    Explanations

    mentions of zombies or zombie-related contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to zombies and zombie-related themes

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

    No Comments

    Negative Logits
    İ
    -0.89
    ī
    -0.76
    ional
    -0.76
    Ķ
    -0.75
    antly
    -0.75
    ĩ
    -0.75
    ours
    -0.75
    ļ
    -0.74
    cipled
    -0.71
    ERC
    -0.70
    POSITIVE LOGITS
     apocalypse
    1.13
    ombies
    1.07
     Apocalypse
    1.04
     horde
    0.97
    ombie
    0.86
     zombies
    0.85
     hordes
    0.84
     zombie
    0.82
     outbreak
    0.80
     Zombies
    0.79
    Activations Density 0.012%

    No Known Activations