© 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. 10-RES-JB
    11. 7920
    Prev
    Next
    INDEX
    Explanations

    dates within text

    oai_token-act-pair · gpt-3.5-turbo

    references to temporal markers indicating time periods, particularly focusing on the words "last" and "this" relating to years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VIDEOS
    -0.73
    ablishment
    -0.67
     Tuesday
    -0.66
     yesterday
    -0.65
    vae
    -0.65
     tomorrow
    -0.65
     Saturdays
    -0.63
     Wednesday
    -0.61
     Genie
    -0.61
     TODAY
    -0.61
    POSITIVE LOGITS
     year
    1.16
    Year
    0.93
     Year
    0.83
    year
    0.80
    2017
    0.74
     season
    0.73
     calendar
    0.73
     semester
    0.72
     yr
    0.72
     YEAR
    0.71
    Activations Density 0.040%

    No Known Activations