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. 16306
    Prev
    Next
    INDEX
    Explanations

    internet domain names ending with ".net"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "net."

    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
    âĺħâĺħ
    -0.70
    sbm
    -0.67
     Barcl
    -0.64
    =-=-=-=-
    -0.64
    HH
    -0.61
    FontSize
    -0.61
     unres
    -0.61
     Templar
    -0.60
    Topic
    -0.59
    =-=-=-=-=-=-=-=-
    -0.59
    POSITIVE LOGITS
    anyahu
    1.39
    izens
    1.36
    izen
    1.33
    sov
    1.11
    working
    1.10
    works
    1.03
    aji
    0.99
    WORK
    0.97
    tering
    0.96
    ted
    0.94
    Activations Density 0.014%

    No Known Activations