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. 13643
    Prev
    Next
    INDEX
    Explanations

    terms related to military equipment and operations, such as artillery, snipers, and helicopters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to military and artillery

    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
    é¾įåĸļ士
    -0.55
    soType
    -0.55
    é¾įå
    -0.54
    cember
    -0.53
    yg
    -0.53
    phrine
    -0.52
    rences
    -0.50
    olon
    -0.50
     princ
    -0.50
    mberg
    -0.50
    POSITIVE LOGITS
     horns
    0.54
    NRS
    0.54
     extraord
    0.50
     hats
    0.50
    Engineers
    0.49
     headlights
    0.49
     nets
    0.49
     electronics
    0.49
     rotor
    0.48
     propulsion
    0.47
    Activations Density 1.444%

    No Known Activations