© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 10418
    Prev
    Next
    INDEX
    Explanations

    references to celestial bodies, particularly the moon

    oai_token-act-pair · gpt-3.5-turbo

    references to the moon

    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
    illance
    -0.72
    IDE
    -0.72
     Maduro
    -0.71
    eq
    -0.70
    nikov
    -0.69
    ocial
    -0.69
     Sark
    -0.67
    ãĥ¤
    -0.67
    Interstitial
    -0.65
     ISI
    -0.65
    POSITIVE LOGITS
    beam
    1.10
    lit
    1.07
     orbiting
    0.97
    light
    0.97
    walking
    0.97
    stone
    0.96
     rover
    0.94
    lighting
    0.94
    rise
    0.92
    stones
    0.89
    Activations Density 0.037%

    No Known Activations