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. 11259
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific country or collective entity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "nation" in various contexts

    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
    omething
    -0.82
    urations
    -0.71
    hift
    -0.71
    IFT
    -0.69
    wrapper
    -0.68
    ension
    -0.67
    err
    -0.66
    pread
    -0.66
     Vaj
    -0.65
    Adds
    -0.65
    POSITIVE LOGITS
    wide
    1.07
    States
    0.75
     sovere
    0.75
    matically
    0.74
    ographically
    0.73
     legislature
    0.72
    agog
    0.71
    ically
    0.71
    urally
    0.70
    ographer
    0.70
    Activations Density 0.028%

    No Known Activations