Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 23393
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the word "Air"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Air" and its related variations, particularly focusing on the context of Airbnb

    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
     Mill
    -0.68
     interpret
    -0.67
     journal
    -0.65
     mature
    -0.64
     format
    -0.64
     decl
    -0.64
     Kru
    -0.63
     perjury
    -0.63
     framed
    -0.63
     lifetime
    -0.62
    POSITIVE LOGITS
    Air
    3.95
    air
    1.99
    AIR
    1.83
    Flight
    1.60
     Air
    1.50
     AIR
    1.42
     air
    1.36
    Jet
    1.30
    Ground
    1.28
    Fire
    1.26
    Activations Density 0.013%

    No Known Activations