© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 7265
    Prev
    Next
    INDEX
    Explanations

    celestial bodies, particularly planets

    oai_token-act-pair · gpt-3.5-turbo

    references to planets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ô
    -0.97
    DOS
    -0.91
    UTH
    -0.79
    Reviewer
    -0.77
    DEP
    -0.75
    displayText
    -0.73
    ulton
    -0.73
     judgment
    -0.73
     Flavoring
    -0.72
    WER
    -0.72
    POSITIVE LOGITS
     orbiting
    1.10
     Ceres
    1.02
    oid
    0.96
    arium
    0.95
    oids
    0.95
     Venus
    0.95
    ouched
    0.94
     Neptune
    0.93
     Pluto
    0.91
     Jupiter
    0.88
    Activations Density 0.009%

    No Known Activations