© 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. 1-RES-JB
    11. 13958
    Prev
    Next
    INDEX
    Explanations

    airline abbreviations, particularly focusing on "WA."

    oai_token-act-pair · gpt-3.5-turbo

    references to the state of Washington

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    croft
    -0.68
    aneous
    -0.65
    displayText
    -0.65
    teenth
    -0.62
     probable
    -0.61
     Dragonbound
    -0.60
     "_
    -0.60
     civ
    -0.60
     Investigator
    -0.58
     otherwise
    -0.57
    POSITIVE LOGITS
    WA
    1.46
    velength
    1.12
    restling
    1.05
    HAHA
    1.04
    HAHAHAHA
    1.02
    UGH
    1.01
    SPA
    0.97
    ufact
    0.96
    orthy
    0.92
    ITNESS
    0.91
    Activations Density 0.007%

    No Known Activations