© 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. 11373
    Prev
    Next
    INDEX
    Explanations

    time-related expressions and future plans

    oai_token-act-pair · gpt-3.5-turbo

    expressions of future expectations or aspirations

    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
    inventoryQuantity
    -0.67
    hess
    -0.64
    jection
    -0.61
    OTOS
    -0.59
    affe
    -0.56
    ĸļ
    -0.56
    avid
    -0.54
    tained
    -0.54
    aeper
    -0.54
    asta
    -0.54
    POSITIVE LOGITS
     will
    1.51
    will
    1.43
    'll
    1.33
     someday
    1.31
     future
    1.27
     WILL
    1.24
     tomorrow
    1.17
    morrow
    1.14
    Will
    1.13
     hereafter
    1.11
    Activations Density 1.717%

    No Known Activations