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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 4099
    Prev
    Next
    INDEX
    Explanations

    terms related to astronomical telescopes

    oai_token-act-pair · gpt-3.5-turbo

    references to telescopes and observatories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    loaded
    -0.67
    fam
    -0.66
    adic
    -0.65
    kl
    -0.64
    leg
    -0.63
     ind
    -0.63
    isma
    -0.61
     aven
    -0.59
     mixed
    -0.59
     opp
    -0.59
    POSITIVE LOGITS
     Telescope
    4.14
     telescope
    2.79
     telescopes
    2.44
     Telesc
    2.20
     Observatory
    1.85
     Hubble
    1.08
     microscope
    1.00
     telesc
    0.98
     eclipse
    0.96
     magnification
    0.95
    Activations Density 0.019%

    No Known Activations