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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16030
    Prev
    Next
    INDEX
    Explanations

    mentions of NASA

    oai_token-act-pair · gpt-3.5-turbo

    mentions of NASA

    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
    cum
    -0.84
    letico
    -0.77
    lass
    -0.76
    swing
    -0.75
    otine
    -0.71
    oldemort
    -0.70
    holder
    -0.69
    manent
    -0.68
    axe
    -0.67
    ablishment
    -0.67
    POSITIVE LOGITS
     Headquarters
    1.01
     Goddard
    0.97
     Ames
    0.91
     Administrator
    0.89
     astronauts
    0.88
     astronaut
    0.84
    ISS
    0.83
     Fisheries
    0.80
    ITED
    0.79
     astronomers
    0.75
    Activations Density 0.020%

    No Known Activations