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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 24327
    Prev
    Next
    INDEX
    Explanations

    mentions of space-related terms and topics

    oai_token-act-pair · gpt-3.5-turbo

    terms specifically related to space and space exploration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umen
    -0.74
    otine
    -0.72
    ause
    -0.70
     Snyder
    -0.69
    igl
    -0.68
     Curve
    -0.65
     Sterling
    -0.64
    ublic
    -0.62
    inger
    -0.61
    ect
    -0.60
    POSITIVE LOGITS
    flight
    1.39
    plane
    1.06
    craft
    1.04
    Engineers
    1.03
    borne
    1.02
     shuttle
    1.01
    planes
    0.97
    kat
    0.94
     exploration
    0.92
     opera
    0.91
    Activations Density 0.032%

    No Known Activations