© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 15818
    Prev
    Next
    INDEX
    Explanations

    references to extraterrestrial beings

    oai_token-act-pair · gpt-3.5-turbo

    references to extraterrestrial life

    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
    nington
    -0.74
    stead
    -0.73
     temper
    -0.68
    rame
    -0.67
    ensive
    -0.65
    kit
    -0.65
    ifestyle
    -0.64
    Activ
    -0.64
    luence
    -0.63
    eanor
    -0.63
    POSITIVE LOGITS
     aliens
    3.18
     Aliens
    2.01
     UFOs
    1.78
     monsters
    1.70
     zombies
    1.69
     ghosts
    1.68
     goblins
    1.64
     elves
    1.61
     vampires
    1.55
     mutants
    1.52
    Activations Density 0.046%

    No Known Activations