© 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. 20435
    Prev
    Next
    INDEX
    Explanations

    keywords related to air travel and aviation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to air or aerial contexts

    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
     dystop
    -0.68
     Pom
    -0.65
    BIT
    -0.64
     Steal
    -0.61
     rooted
    -0.61
    ById
    -0.61
     prol
    -0.60
    FactoryReloaded
    -0.60
     PhD
    -0.59
     stats
    -0.59
    POSITIVE LOGITS
    air
    4.52
    airs
    2.76
    Air
    2.18
    AIR
    2.15
    aired
    1.97
     air
    1.61
    aire
    1.60
     Air
    1.45
     AIR
    1.25
    hair
    1.21
    Activations Density 0.012%

    No Known Activations