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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 7765
    Prev
    Next
    INDEX
    Explanations

    different ways of looking at or thinking about something

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to different perspectives or approaches to understanding a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OTOS
    -0.68
    osponsors
    -0.67
    cover
    -0.64
     ..............
    -0.63
    ikers
    -0.62
     Provided
    -0.61
     blockers
    -0.60
     ][
    -0.60
    umerous
    -0.59
    éļ
    -0.59
    POSITIVE LOGITS
    ety
    0.72
    aign
    0.70
     fare
    0.68
    ilton
    0.68
     structured
    0.66
    grass
    0.63
     phr
    0.62
     interact
    0.62
    riage
    0.61
    ezvous
    0.60
    Activations Density 0.185%

    No Known Activations