© 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. 11-RES-JB
    11. 7623
    Prev
    Next
    INDEX
    Explanations

    phrases related to celestial objects, particularly Earth

    oai_token-act-pair · gpt-3.5-turbo

    references to Earth and related celestial concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ussen
    -0.75
    acco
    -0.64
     Fargo
    -0.62
     htt
    -0.61
    ariat
    -0.60
    Americ
    -0.60
    enges
    -0.59
     Connor
    -0.58
     Cohn
    -0.58
    ession
    -0.58
    POSITIVE LOGITS
    lings
    1.19
     orbit
    1.13
    worms
    1.00
     orbits
    0.99
     Orbit
    0.98
     orbiting
    0.98
    oids
    0.91
    Bound
    0.89
    oid
    0.88
    worm
    0.87
    Activations Density 0.027%

    No Known Activations