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. 1483
    Prev
    Next
    INDEX
    Explanations

    phrases indicating consideration or contemplation

    oai_token-act-pair · gpt-3.5-turbo

    instances of directive phrases that suggest consideration or reflection

    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
    mith
    -0.78
    */(
    -0.68
    iership
    -0.68
    displayText
    -0.67
    wa
    -0.65
    collect
    -0.64
    PATH
    -0.64
    kered
    -0.64
    sell
    -0.64
    IAL
    -0.64
    POSITIVE LOGITS
    amaz
    0.79
    andum
    0.77
     imagine
    0.75
    lihood
    0.74
    nces
    0.71
    nce
    0.70
     Ups
    0.68
    tymology
    0.68
    ings
    0.67
     Examples
    0.66
    Activations Density 0.078%

    No Known Activations