© 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. 21067
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a future time frame

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating future timeframes or projections

    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
     guiActiveUn
    -0.79
    aval
    -0.62
     waived
    -0.61
    ollah
    -0.59
    pointers
    -0.58
    inventoryQuantity
    -0.58
     Cosponsors
    -0.57
     Advertisement
    -0.57
    emouth
    -0.57
    ouses
    -0.55
    POSITIVE LOGITS
     come
    1.52
    come
    1.26
     Come
    1.11
     follow
    1.07
     arrive
    0.95
    ilers
    0.91
     emerge
    0.88
     arise
    0.87
     unfold
    0.81
     2030
    0.81
    Activations Density 0.051%

    No Known Activations