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. 1090
    Prev
    Next
    INDEX
    Explanations

    large amounts, often in the context of money or donations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of amounts of money, particularly those that are $500

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The number 500

    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
    swick
    -0.78
    wered
    -0.78
    ophon
    -0.76
    acia
    -0.75
    warts
    -0.71
    isman
    -0.71
    oglobin
    -0.70
     Osw
    -0.70
    udic
    -0.69
    atic
    -0.69
    POSITIVE LOGITS
    0002
    0.80
     ILCS
    0.79
    px
    0.79
    charg
    0.77
    ESSION
    0.76
    +)
    0.76
    ertodd
    0.76
    000
    0.76
     MHz
    0.73
    +.
    0.73
    Activations Density 0.028%

    No Known Activations