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

    Neuronpedia

    APICircuit 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. 10-RES-JB
    6. 19194
    Prev
    Next
    INDEX
    Explanations

    mentions of or references to aliens

    oai_token-act-pair · gpt-3.5-turbo

    references to extraterrestrial beings or aliens

    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
    okers
    -0.82
    soDeliveryDate
    -0.80
    Ö¼
    -0.80
    rien
    -0.78
    lot
    -0.73
    )].
    -0.72
    oker
    -0.70
    tons
    -0.67
    heet
    -0.67
     Eliot
    -0.66
    POSITIVE LOGITS
     abduction
    1.33
     abduct
    1.13
     invasion
    1.04
     invaders
    1.02
     visitation
    0.99
    ware
    0.98
     aliens
    0.91
    ation
    0.89
     spaceship
    0.88
     Swarm
    0.86
    Activations Density 0.043%

    No Known Activations