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. 12046
    Prev
    Next
    INDEX
    Explanations

    words related to the ancient civilization of Sumer

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sums or totals

    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
    enhagen
    -0.70
    ©¶æ¥µ
    -0.67
     levers
    -0.61
    jriwal
    -0.60
    MRI
    -0.60
     surg
    -0.60
    hent
    -0.59
    atcher
    -0.59
     whiff
    -0.58
     holster
    -0.56
    POSITIVE LOGITS
    ua
    0.75
    zees
    0.72
    atural
    0.66
    ript
    0.64
    oga
    0.62
    dam
    0.61
    ophon
    0.60
    hua
    0.58
    ederal
    0.57
    ST
    0.57
    Activations Density 0.142%

    No Known Activations