© 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. 10-RES-JB
    11. 23184
    Prev
    Next
    INDEX
    Explanations

    references to the planet Mars

    oai_token-act-pair · gpt-3.5-turbo

    references to Mars or Martian concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elist
    -0.80
     deaf
    -0.70
    ombat
    -0.69
     Coulter
    -0.65
    rencies
    -0.65
    oshop
    -0.64
    ocard
    -0.64
     Akin
    -0.63
     Cork
    -0.63
    istical
    -0.62
    POSITIVE LOGITS
     Rover
    1.11
     rover
    1.02
     Orbit
    0.96
     Curiosity
    0.92
     Exploration
    0.90
     orbit
    0.84
     Mars
    0.84
     colonization
    0.84
    iosity
    0.83
     Atmosp
    0.82
    Activations Density 0.016%

    No Known Activations