© 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. 0-RES-JB
    11. 1106
    Prev
    Next
    INDEX
    Explanations

    references to the concept of air

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "air."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jr
    -0.87
    uther
    -0.71
    Hack
    -0.69
    owship
    -0.67
    Wallet
    -0.64
    fully
    -0.64
    Transaction
    -0.63
     Transaction
    -0.63
     Bridgewater
    -0.62
     |--
    -0.61
    POSITIVE LOGITS
     air
    3.81
    Air
    2.39
     Air
    2.34
    air
    2.11
     AIR
    1.97
     airspace
    1.85
     airs
    1.76
     airst
    1.69
     airborne
    1.67
     aer
    1.66
    Activations Density 0.018%

    No Known Activations