© 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. 1-RES-JB
    11. 23600
    Prev
    Next
    INDEX
    Explanations

    prominent mentions of the word "Martian"

    oai_token-act-pair · gpt-3.5-turbo

    references to Mars and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulet
    -1.02
    uer
    -0.91
    ramid
    -0.90
    NetMessage
    -0.88
    reen
    -0.87
    hr
    -0.81
    si
    -0.80
    hm
    -0.80
    rent
    -0.79
    etting
    -0.78
    POSITIVE LOGITS
     Martian
    1.14
     Gladiator
    0.74
     adaptations
    0.73
     Lunar
    0.72
     Mars
    0.72
     Worlds
    0.71
     habitats
    0.69
     rover
    0.69
     colonies
    0.69
     stripes
    0.68
    Activations Density 0.013%

    No Known Activations