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. 18383
    Prev
    Next
    INDEX
    Explanations

    words related to economic issues or financial instability

    oai_token-act-pair · gpt-3.5-turbo

    words related to financial crises and economic downturns

    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
    sembly
    -0.78
     reconc
    -0.70
    anmar
    -0.69
    zhou
    -0.69
    wcs
    -0.69
    ħĭ
    -0.66
    ¯
    -0.66
     congress
    -0.65
    cano
    -0.64
    ascript
    -0.63
    POSITIVE LOGITS
    ernal
    0.89
    ted
    0.87
    TING
    0.80
    iquette
    0.77
    tle
    0.75
    zel
    0.74
    icle
    0.72
    ered
    0.71
    ropolis
    0.70
    tering
    0.70
    Activations Density 0.018%

    No Known Activations