© 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. 11-RES-JB
    11. 10066
    Prev
    Next
    INDEX
    Explanations

    years or specific dates

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to time and significant dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actions
    -0.70
    eston
    -0.66
    houses
    -0.64
     subsidiaries
    -0.63
     dishes
    -0.62
    ãĥ´
    -0.60
     wills
    -0.60
    Room
    -0.59
    ACTION
    -0.58
    chairs
    -0.58
    POSITIVE LOGITS
     anniversary
    1.29
     year
    1.28
     month
    1.23
    Year
    1.14
     busiest
    1.14
     period
    1.13
     Month
    1.11
     epoch
    1.09
     deadline
    1.05
     date
    1.04
    Activations Density 0.150%

    No Known Activations