© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 17688
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking off or departing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "take off."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MX
    -0.62
    ystem
    -0.60
    uddy
    -0.60
     Holo
    -0.60
    Deal
    -0.59
    isma
    -0.59
     Primordial
    -0.58
    =[
    -0.57
    dfx
    -0.57
    Times
    -0.57
    POSITIVE LOGITS
    leaf
    0.74
    screen
    0.74
    shoot
    0.71
     steam
    0.70
     wings
    0.68
    loaded
    0.68
    fall
    0.67
    irgin
    0.66
    enburg
    0.66
     limbs
    0.65
    Activations Density 0.029%

    No Known Activations