© 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
    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. 1646
    Prev
    Next
    INDEX
    Explanations

    information related to space exploration and missions, including details about astronauts, space agencies, spacecraft, and missions to different celestial bodies

    oai_token-act-pair · gpt-3.5-turbo

    information related to space missions and their associated risks and challenges

    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
    à©
    -0.81
     looph
    -0.77
     Lawyers
    -0.71
    inelli
    -0.71
     Scrib
    -0.70
    Ͻ
    -0.69
    Ott
    -0.68
    à¨
    -0.68
     Noir
    -0.68
     Brach
    -0.67
    POSITIVE LOGITS
     astronauts
    1.72
     spacecraft
    1.67
     orbiting
    1.64
     orbit
    1.56
     astronaut
    1.56
     manned
    1.51
     lunar
    1.47
     missions
    1.42
     rover
    1.41
     orbits
    1.38
    Activations Density 0.237%

    No Known Activations