© 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 EvalsExportsAPI 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. 2-RES-JB
    11. 16032
    Prev
    Next
    INDEX
    Explanations

    terms related to space exploration and space technology

    oai_token-act-pair · gpt-3.5-turbo

    references to space exploration and missions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brow
    -0.76
     Snyder
    -0.74
    UCT
    -0.73
    kai
    -0.72
     Rove
    -0.68
    Financial
    -0.65
     Die
    -0.63
    IELD
    -0.63
     Roth
    -0.63
     Simpson
    -0.62
    POSITIVE LOGITS
     space
    1.04
    gravity
    1.00
    flight
    0.94
     shuttle
    0.94
    plane
    0.93
     habitats
    0.92
     footprint
    0.90
    ngth
    0.85
    Space
    0.84
    space
    0.83
    Activations Density 0.018%

    No Known Activations