© 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. 7-RES-JB
    6. 17295
    Prev
    Next
    INDEX
    Explanations

    time durations expressed in minutes and seconds

    oai_token-act-pair · gpt-3.5-turbo

    events related to space missions and launches

    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
    acist
    -0.85
    conom
    -0.84
    soType
    -0.82
    law
    -0.80
    street
    -0.80
     Tavern
    -0.80
    geist
    -0.79
     Anarch
    -0.79
     Violent
    -0.78
    enfranch
    -0.78
    POSITIVE LOGITS
     spacecraft
    1.49
     astronauts
    1.40
     aboard
    1.32
     orbit
    1.29
     NASA
    1.29
    NASA
    1.28
     satellites
    1.28
     rover
    1.26
     orbiting
    1.22
     propulsion
    1.21
    Activations Density 0.592%

    No Known Activations