© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 3131
    Prev
    Next
    INDEX
    Explanations

    time expressions related to the term "week"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "this" as a reference to time or context

    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
    rics
    -0.65
    keye
    -0.64
    ques
    -0.62
    erk
    -0.62
    eez
    -0.62
    cks
    -0.61
    asures
    -0.61
    lees
    -0.61
    gans
    -0.61
     Nib
    -0.61
    POSITIVE LOGITS
     week
    1.37
     month
    1.25
     morning
    1.21
     weekend
    1.15
     afternoon
    1.15
     year
    1.06
     evening
    0.98
     WEEK
    0.95
     summer
    0.93
    morning
    0.86
    Activations Density 0.121%

    No Known Activations