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. 5715
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names ending with the letter 'K'

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals

    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
     wide
    -0.74
    assetsadobe
    -0.68
     ......
    -0.65
     Voc
    -0.65
     âĢº
    -0.62
     (?,
    -0.61
     ______
    -0.61
     meg
    -0.61
    ::::::::
    -0.60
     Tradable
    -0.58
    POSITIVE LOGITS
    SF
    0.75
    utter
    0.74
    yon
    0.71
    atten
    0.69
    aney
    0.68
    assi
    0.67
    MN
    0.65
    wise
    0.65
    OH
    0.65
    OSE
    0.65
    Activations Density 0.283%

    No Known Activations