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. 7727
    Prev
    Next
    INDEX
    Explanations

    words related to coverings, whether literal or figurative

    oai_token-act-pair · gpt-3.5-turbo

    the word "blanket" and its variations, indicating discussions about coverage, protection, or metaphorical uses of the term

    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
    ymes
    -0.75
    ctions
    -0.71
     resil
    -0.69
     Naz
    -0.62
    tics
    -0.62
    sych
    -0.60
     Oro
    -0.59
    Ķ
    -0.59
     admirable
    -0.59
    module
    -0.59
    POSITIVE LOGITS
     blanket
    1.24
    abies
    0.86
     COVER
    0.84
    sheets
    0.83
     blankets
    0.83
    eding
    0.80
    krit
    0.78
    wart
    0.74
    aby
    0.73
    spread
    0.73
    Activations Density 0.019%

    No Known Activations