© 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. 10-RES-JB
    11. 1342
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an action or event that has not happened yet

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "yet to be" and its variations in reference to actions or statuses that have not occurred

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.78
     Veh
    -0.78
    channelAvailability
    -0.66
     teasp
    -0.59
    pill
    -0.58
    âĹ¼
    -0.58
     weap
    -0.58
     Keeping
    -0.58
     Sweep
    -0.58
    Protect
    -0.58
    POSITIVE LOGITS
     formally
    1.05
     finalized
    0.97
     officially
    0.92
     satisf
    0.90
     fully
    0.87
    icable
    0.86
     formal
    0.85
     definitively
    0.82
     disclose
    0.82
     decide
    0.81
    Activations Density 0.093%

    No Known Activations