© 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. 11-RES-JB
    11. 17201
    Prev
    Next
    INDEX
    Explanations

    words related to the mission of the spacecraft Rosetta

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events related to space exploration missions

    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
    mong
    -0.80
     Asians
    -0.80
    otine
    -0.78
     Rohing
    -0.78
     malls
    -0.77
     Mong
    -0.77
     Rohingya
    -0.77
     Sharia
    -0.76
     Dill
    -0.75
     Lawyers
    -0.74
    POSITIVE LOGITS
     comet
    1.60
     Pluto
    1.57
     spacecraft
    1.43
     Voyager
    1.37
     orbits
    1.26
     Comet
    1.25
     Jupiter
    1.23
     orbit
    1.20
     Hubble
    1.20
     Horizons
    1.20
    Activations Density 0.139%

    No Known Activations