© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 17605
    Prev
    Next
    INDEX
    Explanations

    information related to the "Alien" movie franchise and the belief in extraterrestrial beings

    oai_token-act-pair · gpt-3.5-turbo

    assertions about the existence or creation of aliens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ©
    -0.90
     Knicks
    -0.87
    ÅĤ
    -0.86
     Taj
    -0.84
     Cohn
    -0.83
     streetcar
    -0.82
    tsky
    -0.82
    oshenko
    -0.80
    CSS
    -0.80
    heast
    -0.80
    POSITIVE LOGITS
     Alien
    2.34
     Aliens
    2.29
    Alien
    2.20
     Ridley
    2.05
     Prometheus
    1.75
     aliens
    1.64
     Predator
    1.63
     alien
    1.55
     Xen
    1.53
    alien
    1.48
    Activations Density 0.205%

    No Known Activations