Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 9669
    Prev
    Next
    INDEX
    Explanations

    time-related information, specifically occurrences since a particular point in time

    oai_token-act-pair · gpt-3.5-turbo

    temporal expressions related to time frames or periods

    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
     voic
    -0.72
    ansk
    -0.71
     blasp
    -0.68
    Die
    -0.65
     somew
    -0.65
    cipl
    -0.65
    alian
    -0.62
     perish
    -0.61
    dimensional
    -0.60
     communicates
    -0.60
    POSITIVE LOGITS
     1990
    1.14
     1980
    1.14
     2000
    1.11
     2008
    1.09
     recession
    1.08
     enactment
    1.07
     2005
    1.05
     2007
    1.05
     2004
    1.03
     1970
    1.03
    Activations Density 0.210%

    No Known Activations