Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 12823
    Prev
    Next
    INDEX
    Explanations

    references to the planet Mars

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Mars or related celestial terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elist
    -0.79
     deaf
    -0.77
    ocard
    -0.69
    ombat
    -0.68
     creditor
    -0.68
    rencies
    -0.68
    oshop
    -0.67
    SPONSORED
    -0.66
    istical
    -0.64
    -----------
    -0.63
    POSITIVE LOGITS
     Rover
    1.13
     Orbit
    1.00
     rover
    1.00
     Curiosity
    0.88
     Exploration
    0.87
     Mars
    0.86
     orbit
    0.83
     Colony
    0.81
     colonization
    0.79
     Atmosp
    0.78
    Activations Density 0.024%

    No Known Activations