Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 6478
    Prev
    Next
    INDEX
    Explanations

    mentions of telescopes

    oai_token-act-pair · gpt-3.5-turbo

    references to telescopes and astronomical observatories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quote
    -0.76
    mix
    -0.76
    ifest
    -0.75
    eem
    -0.74
     Leilan
    -0.74
    ovic
    -0.73
    lass
    -0.73
    estyle
    -0.71
     Adidas
    -0.69
    BuyableInstoreAndOnline
    -0.69
    POSITIVE LOGITS
     telescope
    1.22
     Telescope
    1.21
     telescopes
    1.13
     astronomers
    0.98
    sonian
    0.96
     astronomer
    0.91
     Hubble
    0.88
     microscope
    0.84
     Observatory
    0.79
     microsc
    0.78
    Activations Density 0.031%

    No Known Activations