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. 21802
    Prev
    Next
    INDEX
    Explanations

    websites by detecting URLs starting with "www"

    oai_token-act-pair · gpt-3.5-turbo

    URLs that start with "www"

    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
     Ballard
    -0.73
     Manifest
    -0.72
     Labrador
    -0.68
     Vaj
    -0.68
     Nadu
    -0.67
     surn
    -0.66
    icted
    -0.64
    oted
    -0.64
    essa
    -0.63
     Loans
    -0.63
    POSITIVE LOGITS
    www
    1.31
    ://
    1.05
    natureconservancy
    1.03
     www
    1.02
    twitter
    0.93
    forum
    0.91
    sites
    0.89
    ww
    0.87
    docs
    0.85
    doi
    0.82
    Activations Density 0.009%

    No Known Activations