© 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. 3961
    Prev
    Next
    INDEX
    Explanations

    specific mentions of airlines in text

    oai_token-act-pair · gpt-3.5-turbo

    references to airlines

    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
    Hill
    -0.75
    imens
    -0.71
    uces
    -0.71
    itia
    -0.68
    laus
    -0.68
    ector
    -0.66
    VK
    -0.65
    ests
    -0.64
     Patriarch
    -0.64
    utenberg
    -0.63
    POSITIVE LOGITS
     airline
    1.06
     Airlines
    1.05
     airlines
    0.97
     boarding
    0.88
     pigeon
    0.87
     hangar
    0.85
     carrier
    0.85
     carriers
    0.83
     passenger
    0.82
     flights
    0.81
    Activations Density 0.009%

    No Known Activations