© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 22902
    Prev
    Next
    INDEX
    Explanations

    references to space missions, particularly those related to the Apollo program and astronauts like Neil Armstrong

    oai_token-act-pair · gpt-3.5-turbo

    references to the Apollo space missions and Neil Armstrong

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idian
    -0.85
    lag
    -0.79
    rier
    -0.76
    nown
    -0.72
    riers
    -0.71
    liam
    -0.70
    aws
    -0.68
    ipped
    -0.67
     Nare
    -0.67
    merga
    -0.67
    POSITIVE LOGITS
     Creed
    1.01
     Apollo
    0.80
    ounters
    0.80
     Pil
    0.72
    osterone
    0.72
    ollo
    0.71
     Armstrong
    0.68
     Resurrection
    0.68
    ovies
    0.68
    uria
    0.68
    Activations Density 0.042%

    No Known Activations