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. 0-RES-JB
    6. 24209
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of zombies

    oai_token-act-pair · gpt-3.5-turbo

    references to zombies and the undead

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fah
    -0.77
     FISA
    -0.76
     Mercury
    -0.74
     Conduct
    -0.73
    rans
    -0.72
    ometers
    -0.71
    ouver
    -0.70
    Chart
    -0.70
     Pearson
    -0.69
     Pratt
    -0.69
    POSITIVE LOGITS
     zombie
    3.38
     Zombie
    3.30
     zombies
    3.11
     Zombies
    2.94
     undead
    2.36
    ombie
    2.10
    ombies
    1.84
     Undead
    1.82
     simulac
    1.78
     skeletons
    1.77
    Activations Density 0.028%

    No Known Activations