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. 13652
    Prev
    Next
    INDEX
    Explanations

    official titles and positions within government or legal contexts

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles related to government officials and law enforcement

    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
    NetMessage
    -0.79
     hots
    -0.67
    ankind
    -0.64
     gamble
    -0.63
    urious
    -0.63
    iland
    -0.58
     cheapest
    -0.58
     trem
    -0.58
    rero
    -0.58
     cafes
    -0.58
    POSITIVE LOGITS
     Ake
    0.86
    awei
    0.75
    ibrarian
    0.73
    utenant
    0.71
    rees
    0.71
    uties
    0.69
    hak
    0.68
    arthed
    0.68
     Cortex
    0.66
     Kodi
    0.66
    Activations Density 0.152%

    No Known Activations