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

    Neuronpedia

    APICircuit 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. 8-RES-JB
    6. 8699
    Prev
    Next
    INDEX
    Explanations

    time-related activities or durations

    oai_token-act-pair · gpt-3.5-turbo

    durations and time-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ranch
    -0.63
    ollo
    -0.63
    brow
    -0.60
     Caption
    -0.56
    ilde
    -0.55
    rites
    -0.55
    ELL
    -0.55
    ãĥķãĤ©
    -0.54
     valves
    -0.52
     fly
    -0.51
    POSITIVE LOGITS
     awhile
    1.55
     eternity
    1.23
     longer
    1.23
     hours
    1.21
    hours
    1.11
     months
    1.10
     weeks
    1.08
     decades
    1.08
    months
    1.05
     years
    1.05
    Activations Density 0.580%

    No Known Activations