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. 18318
    Prev
    Next
    INDEX
    Explanations

    URLs and website domains

    oai_token-act-pair · gpt-3.5-turbo

    mentions of domain names and web sources

    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
     mirac
    -0.68
     decap
    -0.64
     Gins
    -0.63
     scept
    -0.62
     situ
    -0.61
     dazz
    -0.59
     demoral
    -0.59
     laz
    -0.59
     realistically
    -0.58
     overd
    -0.58
    POSITIVE LOGITS
     tradem
    0.89
    ĨĴ
    0.79
    eport
    0.77
    taboola
    0.77
    sites
    0.73
     Printed
    0.73
     Accessed
    0.72
    «ĺ
    0.72
     Gutenberg
    0.71
    facebook
    0.70
    Activations Density 0.162%

    No Known Activations