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. 8-RES-JB
    6. 5374
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences referring to implications or consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate implications or consequences

    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
    iliate
    -0.76
    uded
    -0.75
    atech
    -0.70
    thumbnails
    -0.70
    oked
    -0.68
    ortex
    -0.68
    taboola
    -0.67
    oqu
    -0.67
    ics
    -0.66
    iazep
    -0.65
    POSITIVE LOGITS
     goodbye
    1.06
     fewer
    0.80
     nothing
    0.79
     abandoning
    0.71
     sacrificing
    0.71
    LOS
    0.71
     everything
    0.70
     anything
    0.68
    little
    0.67
     something
    0.67
    Activations Density 0.047%

    No Known Activations