© 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. 16250
    Prev
    Next
    INDEX
    Explanations

    phrases containing words related to questioning or inquiry

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "quest" in various forms

    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
     spare
    -0.78
     concentration
    -0.68
     smoker
    -0.64
     habit
    -0.64
     swinging
    -0.62
     neat
    -0.62
     smoke
    -0.61
     elbows
    -0.61
     bath
    -0.60
    hiba
    -0.60
    POSITIVE LOGITS
    quest
    1.27
    naire
    1.21
    ioned
    1.15
    naires
    1.08
    ions
    0.88
    rade
    0.86
     Questions
    0.80
    dale
    0.78
    ion
    0.76
    ION
    0.75
    Activations Density 0.007%

    No Known Activations