© 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. 2-RES-JB
    11. 18361
    Prev
    Next
    INDEX
    Explanations

    time-related durations expressed in weeks

    oai_token-act-pair · gpt-3.5-turbo

    references to durations of time, specifically in weeks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jri
    -0.72
     constitu
    -0.70
     culp
    -0.64
    ifice
    -0.62
     superflu
    -0.61
     Cir
    -0.60
     racially
    -0.60
     misunderstanding
    -0.60
    EStream
    -0.60
     cogn
    -0.59
    POSITIVE LOGITS
    days
    1.19
    iversary
    1.07
    DAY
    1.02
    day
    0.98
    iday
    0.96
    week
    0.96
    andowski
    0.95
    night
    0.95
    orrow
    0.93
    uty
    0.91
    Activations Density 0.010%

    No Known Activations