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. 2-RES-JB
    6. 4651
    Prev
    Next
    INDEX
    Explanations

    references to outer space or space-related entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Space."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kai
    -0.78
    posted
    -0.70
    heit
    -0.69
     presumptive
    -0.65
     rewarding
    -0.64
     pronounced
    -0.63
    代
    -0.63
     Roth
    -0.62
     behold
    -0.62
     Snyder
    -0.62
    POSITIVE LOGITS
    Space
    0.99
     Spaces
    0.94
     Space
    0.92
     Patrol
    0.88
     Orbit
    0.85
     Station
    0.84
     Advisor
    0.82
    craft
    0.82
    Engineers
    0.81
     Horizons
    0.80
    Activations Density 0.010%

    No Known Activations