© 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 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. 13005
    Prev
    Next
    INDEX
    Explanations

    the word "sometime" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to unspecified future times or events

    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
    Emb
    -0.62
    DIV
    -0.58
    pool
    -0.57
    stract
    -0.56
    ubi
    -0.56
     nor
    -0.56
    pert
    -0.55
    roud
    -0.54
    arest
    -0.54
     endorsements
    -0.53
    POSITIVE LOGITS
     sometime
    3.38
    ometime
    1.93
     someday
    1.88
     awhile
    1.42
     somewhere
    1.35
     shortly
    1.34
     somew
    1.29
     sooner
    1.27
     circa
    1.16
     soon
    1.16
    Activations Density 0.010%

    No Known Activations