© 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. 11-RES-JB
    11. 6832
    Prev
    Next
    INDEX
    Explanations

    words related to the atmosphere and environmental components, particularly related to air and ground

    oai_token-act-pair · gpt-3.5-turbo

    connections or relationships involving environmental elements and their impact

    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
     Franç
    -0.81
     doct
    -0.66
     Deal
    -0.65
    den
    -0.64
     Lifetime
    -0.64
     shorthand
    -0.63
     Annie
    -0.62
    Skip
    -0.62
     Fail
    -0.61
    Hack
    -0.61
    POSITIVE LOGITS
     oceans
    1.51
     skies
    1.45
     seas
    1.42
     sea
    1.42
    sea
    1.36
     rivers
    1.32
     ocean
    1.24
     groundwater
    1.22
     sky
    1.21
     airspace
    1.21
    Activations Density 0.168%

    No Known Activations