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

    Neuronpedia

    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. 8-RES-JB
    11. 2110
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the moon

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Moon" and related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    axter
    -0.82
    iability
    -0.78
    hered
    -0.72
     Mellon
    -0.71
    tery
    -0.66
    thodox
    -0.65
    \<
    -0.63
    sburgh
    -0.62
    illac
    -0.61
    leneck
    -0.61
    POSITIVE LOGITS
    beam
    1.22
    lit
    0.97
    stru
    0.97
    phase
    0.89
    walker
    0.87
     Jae
    0.86
    lite
    0.85
    rise
    0.84
    lighting
    0.84
    walking
    0.84
    Activations Density 0.032%

    No Known Activations