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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 9559
    Prev
    Next
    INDEX
    Explanations

    terms related to the planet Mars

    oai_token-act-pair · gpt-3.5-turbo

    references to Mars and its features

    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
     Coulter
    -0.76
     Cantor
    -0.71
     deaf
    -0.70
    elist
    -0.68
     Akin
    -0.67
    SPONSORED
    -0.66
    ombat
    -0.66
    unci
    -0.65
     Cork
    -0.65
    zzi
    -0.64
    POSITIVE LOGITS
     Rover
    1.10
     rover
    1.07
     Exploration
    1.04
     Orbit
    0.98
     Curiosity
    0.96
    iosity
    0.91
     colonization
    0.91
     colonists
    0.88
     exploration
    0.88
     Atmosp
    0.87
    Activations Density 0.024%

    No Known Activations