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. 9-RES-JB
    6. 16808
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to space exploration

    oai_token-act-pair · gpt-3.5-turbo

    references to space exploration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inger
    -0.70
    otine
    -0.68
     scrut
    -0.68
    UCT
    -0.65
    usted
    -0.65
     Snyder
    -0.64
     Brow
    -0.62
    ered
    -0.62
    venge
    -0.60
    ielding
    -0.60
    POSITIVE LOGITS
    flight
    1.27
    plane
    1.01
    Engineers
    1.00
    gravity
    0.96
     shuttle
    0.94
    planes
    0.94
    craft
    0.93
     Exploration
    0.91
     exploration
    0.89
    borne
    0.89
    Activations Density 0.035%

    No Known Activations