Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 17753
    Prev
    Next
    INDEX
    Explanations

    keywords related to antivirus software and cybersecurity companies

    oai_token-act-pair · gpt-3.5-turbo

    references to antivirus software and cybersecurity

    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
    erent
    -0.74
    erer
    -0.74
    bodied
    -0.73
    NM
    -0.68
    ezvous
    -0.67
    mitt
    -0.66
    sth
    -0.66
    mt
    -0.63
    tera
    -0.63
    bered
    -0.63
    POSITIVE LOGITS
     Mehran
    0.91
     scanners
    0.85
    DragonMagazine
    0.85
    irus
    0.83
    aspers
    0.75
     screenings
    0.74
     antiv
    0.74
     Laboratories
    0.74
    ware
    0.72
     warnings
    0.69
    Activations Density 0.027%

    No Known Activations