Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 19454
    Prev
    Next
    INDEX
    Explanations

    the word "anytime" occurring in contexts indicating a future event

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "anytime soon" in various contexts

    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
    rity
    -0.55
    iple
    -0.53
     tentative
    -0.51
     Tro
    -0.50
    cul
    -0.50
    str
    -0.50
     Slav
    -0.50
    spl
    -0.49
    ir
    -0.49
    uding
    -0.49
    POSITIVE LOGITS
     anytime
    3.78
     anywhere
    1.48
     whenever
    1.38
     someday
    1.27
     any
    1.13
     ANY
    1.11
     anymore
    1.10
    any
    1.07
     wherever
    1.04
    omever
    1.01
    Activations Density 0.006%

    No Known Activations