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. 20085
    Prev
    Next
    INDEX
    Explanations

    phrases related to varied personal experiences and observations

    oai_token-act-pair · gpt-3.5-turbo

    expressions and phrases related to personal experiences and reflections

    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
    adden
    -0.81
    ellar
    -0.69
    conservancy
    -0.65
    othermal
    -0.61
     aggregation
    -0.61
     honoured
    -0.60
    ensical
    -0.59
    ensible
    -0.59
    inka
    -0.59
    ensibly
    -0.59
    POSITIVE LOGITS
     etc
    1.06
    etc
    0.82
     Lastly
    0.80
    whatever
    0.79
     Finally
    0.77
     Prest
    0.76
     Divide
    0.75
     Difference
    0.74
     Again
    0.73
    Trivia
    0.73
    Activations Density 0.827%

    No Known Activations