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. 11-RES-JB
    6. 8110
    Prev
    Next
    INDEX
    Explanations

    terms related to firearms, gun control, and gun violence

    oai_token-act-pair · gpt-3.5-turbo

    references to gun-related topics or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     compounded
    -0.65
     coli
    -0.64
     disson
    -0.64
     candles
    -0.63
     Quentin
    -0.62
     orphans
    -0.60
     sincerely
    -0.60
     Richards
    -0.60
     Icelandic
    -0.59
     adults
    -0.59
    POSITIVE LOGITS
    carry
    1.36
    mounted
    1.27
    length
    1.22
    related
    1.21
    bearing
    1.21
    safety
    1.20
    sized
    1.19
    equipped
    1.17
    training
    1.17
    sharing
    1.16
    Activations Density 0.077%

    No Known Activations