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. 20629
    Prev
    Next
    INDEX
    Explanations

    numerical references to future years, especially related to environmental targets or predictions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years, particularly 2030 and 2050

    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
    afort
    -0.81
    verbs
    -0.73
    abilia
    -0.71
    uid
    -0.69
    ando
    -0.67
    tub
    -0.66
    isy
    -0.66
    yl
    -0.66
    ql
    -0.64
    iqu
    -0.64
    POSITIVE LOGITS
     2025
    1.00
     2050
    0.93
    ãĤ¼ãĤ¦ãĤ¹
    0.92
     2030
    0.92
     onwards
    0.82
    abad
    0.82
     onward
    0.81
     2021
    0.81
     2020
    0.76
     Ceres
    0.74
    Activations Density 0.015%

    No Known Activations