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. 3811
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Chase" followed by a number that indicates the noun's importance in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Chase."

    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
    atics
    -0.80
    etheless
    -0.79
    eatures
    -0.78
    hops
    -0.77
    aciously
    -0.74
    aced
    -0.71
    aution
    -0.70
     exha
    -0.69
    quartered
    -0.69
    itely
    -0.68
    POSITIVE LOGITS
     Chase
    1.05
     Sapphire
    0.76
    berry
    0.74
    weed
    0.73
    berries
    0.69
     Cars
    0.68
     Masters
    0.68
    MENTS
    0.67
     JPM
    0.66
     Bryant
    0.65
    Activations Density 0.023%

    No Known Activations