© 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. 7-RES-JB
    11. 14642
    Prev
    Next
    INDEX
    Explanations

    planets and celestial bodies related to the solar system

    oai_token-act-pair · gpt-3.5-turbo

    references to celestial bodies, particularly planets and their characteristics in relation to the sun

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĭ
    -0.89
    roup
    -0.77
    sbm
    -0.76
    Coun
    -0.73
    UFC
    -0.73
    iken
    -0.72
     Homeless
    -0.71
    igun
    -0.71
    APD
    -0.70
    Hong
    -0.69
    POSITIVE LOGITS
    arium
    0.98
     orbiting
    0.95
     orbits
    0.94
    oids
    0.92
     orb
    0.85
     Observatory
    0.85
     Orbit
    0.84
     orbit
    0.83
     Uran
    0.82
    oid
    0.81
    Activations Density 0.073%

    No Known Activations