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. 8786
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic articles, publications, and studies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant events or conditions affecting society

    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
    ather
    -0.75
    tein
    -0.70
    xual
    -0.67
    TAG
    -0.64
    terior
    -0.64
     payload
    -0.63
    activation
    -0.63
    insk
    -0.62
    zi
    -0.62
    colo
    -0.62
    POSITIVE LOGITS
     skyline
    0.76
     Liberties
    0.75
     legislature
    0.75
     ILCS
    0.72
    ptroller
    0.71
     highways
    0.67
    NetMessage
    0.66
     electing
    0.66
     municipalities
    0.66
     landmark
    0.65
    Activations Density 0.731%

    No Known Activations