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. 9-RES-JB
    6. 21577
    Prev
    Next
    INDEX
    Explanations

    time-related information, particularly the duration or starting point of events or actions

    oai_token-act-pair · gpt-3.5-turbo

    the usage of the word "since" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    potion
    -0.81
    pta
    -0.76
    obook
    -0.74
    anie
    -0.74
    natureconservancy
    -0.72
     Traps
    -0.68
    LED
    -0.66
    Enhanced
    -0.66
    Guide
    -0.66
    vantage
    -0.65
    POSITIVE LOGITS
     inception
    1.21
     infancy
    1.06
     January
    1.06
     October
    1.03
     1999
    1.03
     September
    1.02
     November
    1.02
     1979
    1.01
     2009
    1.01
     December
    1.00
    Activations Density 0.046%

    No Known Activations