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. 10-RES-JB
    6. 11808
    Prev
    Next
    INDEX
    Explanations

    mentions of time durations, such as "a couple of months" or "a very long time"

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the duration and progression of time

    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
    interstitial
    -0.57
    robat
    -0.56
    rikes
    -0.54
     later
    -0.54
    aterasu
    -0.52
    ucker
    -0.51
    oids
    -0.50
     Caption
    -0.50
    rals
    -0.50
    %%
    -0.50
    POSITIVE LOGITS
     YEAR
    1.16
     decade
    1.00
     awhile
    0.97
    years
    0.92
     years
    0.90
     decades
    0.84
     ages
    0.82
    since
    0.79
     longest
    0.79
     LONG
    0.78
    Activations Density 0.145%

    No Known Activations