© 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. 4-RES-JB
    11. 7443
    Prev
    Next
    INDEX
    Explanations

    phrases related to the Mars Rover mission

    oai_token-act-pair · gpt-3.5-turbo

    references to space exploration vehicles, particularly rovers and their missions

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

    No Comments

    Negative Logits
    irl
    -0.85
    ames
    -0.81
    otine
    -0.76
    lass
    -0.75
    elist
    -0.73
    annon
    -0.72
    oho
    -0.72
    panic
    -0.72
    ulin
    -0.70
    abet
    -0.70
    POSITIVE LOGITS
     Curiosity
    1.40
     rover
    1.39
     Rover
    1.23
     Expedition
    0.78
    iosity
    0.77
     Mars
    0.77
     Mission
    0.74
     missions
    0.72
     astronauts
    0.71
     expedition
    0.70
    Activations Density 0.007%

    No Known Activations