© 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. 2-RES-JB
    11. 24107
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "air"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "air."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Principles
    -0.76
     Cla
    -0.76
     Kuh
    -0.67
    enance
    -0.67
    ettings
    -0.66
     Burgess
    -0.66
     Flores
    -0.62
    initions
    -0.62
     Ll
    -0.61
     Cumber
    -0.61
    POSITIVE LOGITS
    waves
    1.24
    plane
    1.13
    bnb
    1.08
    planes
    0.99
     conditioning
    0.91
    raid
    0.86
    dro
    0.81
    mail
    0.80
     air
    0.79
     ventilation
    0.78
    Activations Density 0.021%

    No Known Activations