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. 8-RES-JB
    6. 16399
    Prev
    Next
    INDEX
    Explanations

    time-related phrases or deadlines

    oai_token-act-pair · gpt-3.5-turbo

    information related to project timelines and deadlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     summed
    -0.70
    Reviewer
    -0.66
     wrongly
    -0.62
     raged
    -0.62
     outnumbered
    -0.61
     erupted
    -0.60
     spawned
    -0.60
     aloud
    -0.59
     ventured
    -0.59
     gripped
    -0.59
    POSITIVE LOGITS
     2019
    1.38
     2020
    1.25
     2021
    1.22
    2019
    1.18
     2018
    1.09
    morrow
    1.08
    2020
    1.05
     tomorrow
    1.03
    uesday
    1.02
     2024
    1.01
    Activations Density 0.417%

    No Known Activations