© 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. 1-RES-JB
    11. 22662
    Prev
    Next
    INDEX
    Explanations

    words related to telescopes

    oai_token-act-pair · gpt-3.5-turbo

    references to telescopes and related astronomical observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    no
    -0.86
    Interstitial
    -0.77
    ne
    -0.75
    estate
    -0.70
    state
    -0.68
    nex
    -0.68
    vo
    -0.67
    death
    -0.65
    non
    -0.65
    dom
    -0.65
    POSITIVE LOGITS
     Telescope
    1.40
     telescope
    1.34
     telescopes
    1.29
    sonian
    1.08
     astronomer
    0.97
     astronomers
    0.96
     glasses
    0.84
     Starg
    0.84
     Observatory
    0.84
     ey
    0.82
    Activations Density 0.009%

    No Known Activations