© 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. 8-RES-JB
    11. 6419
    Prev
    Next
    INDEX
    Explanations

    references to extraterrestrial beings and related concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to aliens and extraterrestrial themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    okers
    -0.92
    oker
    -0.82
     Mellon
    -0.77
    hirt
    -0.76
    YR
    -0.73
    arf
    -0.73
    Ö¼
    -0.73
    heet
    -0.72
    theless
    -0.68
    soDeliveryDate
    -0.68
    POSITIVE LOGITS
     abduction
    1.36
     abduct
    1.15
     visitation
    1.01
     invasion
    0.98
     invaders
    0.91
     species
    0.85
     extrater
    0.85
     civilizations
    0.84
     aliens
    0.83
     Aliens
    0.82
    Activations Density 0.034%

    No Known Activations