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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 7637
    Prev
    Next
    INDEX
    Explanations

    weapons, tools, and equipment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to military resources and assets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cus
    -0.71
    occ
    -0.70
    aho
    -0.68
     Johann
    -0.67
    igi
    -0.67
    birth
    -0.66
    light
    -0.66
     pilgrims
    -0.66
     Dian
    -0.65
    tale
    -0.65
    POSITIVE LOGITS
     arsenal
    1.09
    eers
    0.87
     repertoire
    0.86
     chops
    0.78
     stockpile
    0.73
    ilogy
    0.73
     reperto
    0.72
     trove
    0.70
     defences
    0.68
     stockp
    0.68
    Activations Density 0.013%

    No Known Activations