© 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. 0-RES-JB
    11. 14936
    Prev
    Next
    INDEX
    Explanations

    phrases related to current events or ongoing actions

    oai_token-act-pair · gpt-3.5-turbo

    the word "currently" indicating ongoing actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rites
    -0.65
    verbal
    -0.60
    ãĥĥãĥī
    -0.59
    enture
    -0.58
    ricular
    -0.58
     gratification
    -0.57
    zes
    -0.57
    reads
    -0.57
    night
    -0.56
    ewitness
    -0.56
    POSITIVE LOGITS
     currently
    3.41
     presently
    2.65
    currently
    2.55
     Currently
    2.08
    Currently
    1.98
     current
    1.64
     already
    1.41
     now
    1.36
    Current
    1.28
     normally
    1.25
    Activations Density 0.017%

    No Known Activations