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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 2640
    Prev
    Next
    INDEX
    Explanations

    terms related to the Earth's atmosphere such as atmospheric content, pressure, gases, layers, and greenhouse effect

    oai_token-act-pair · gpt-3.5-turbo

    references to atmospheric conditions and components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    practice
    -0.76
    Union
    -0.73
     Barbar
    -0.73
     IMAGES
    -0.65
    udeb
    -0.65
    EE
    -0.64
    odore
    -0.63
    Corp
    -0.63
    Vert
    -0.62
    POS
    -0.62
    POSITIVE LOGITS
    heric
    1.11
     ozone
    1.09
     gases
    0.95
     atmosp
    0.92
     helium
    0.90
    osphere
    0.90
     conducive
    0.88
     turbulence
    0.87
     pollutants
    0.87
     methane
    0.86
    Activations Density 0.047%

    No Known Activations