© 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. 15176
    Prev
    Next
    INDEX
    Explanations

    Mars-related terms or references

    oai_token-act-pair · gpt-3.5-turbo

    references to Mars and its environment

    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
    elist
    -0.81
    oshop
    -0.72
    ocard
    -0.71
     deaf
    -0.71
    rencies
    -0.70
    OWN
    -0.70
    ibus
    -0.68
    -----------
    -0.66
     creditor
    -0.64
    irl
    -0.63
    POSITIVE LOGITS
     Rover
    1.13
     Orbit
    0.94
     rover
    0.91
     Exploration
    0.86
     Mars
    0.84
     habitats
    0.84
     Curiosity
    0.81
     colonization
    0.81
     biome
    0.79
     colonists
    0.79
    Activations Density 0.024%

    No Known Activations