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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3429
    Prev
    Next
    INDEX
    Explanations

    phrases related to versatile locations or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "anywhere" or locations without restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.71
    Spoiler
    -0.66
    ItemTracker
    -0.66
    bda
    -0.65
    qus
    -0.64
    orously
    -0.61
    ror
    -0.61
    orically
    -0.60
    interstitial
    -0.59
     Rue
    -0.59
    POSITIVE LOGITS
     imaginable
    1.48
     anytime
    1.06
     anywhere
    1.03
    soever
    1.01
     conceivable
    0.95
     regardless
    0.94
     whatsoever
    0.91
    any
    0.82
     anybody
    0.81
     else
    0.80
    Activations Density 0.118%

    No Known Activations