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. 875
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to explosives

    oai_token-act-pair · gpt-3.5-turbo

    terms related to explosives and their use

    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
    aird
    -0.83
     Seah
    -0.76
    Sea
    -0.74
     Vale
    -0.73
    SEA
    -0.72
     Stream
    -0.69
     Agric
    -0.68
     Volunte
    -0.68
     Overt
    -0.68
    adapt
    -0.67
    POSITIVE LOGITS
     detonated
    1.45
     deton
    1.28
     explosives
    1.19
     grenades
    1.03
     barric
    1.00
     disposal
    0.96
     grenade
    0.95
    ilitary
    0.94
     breaching
    0.90
     bombs
    0.89
    Activations Density 0.039%

    No Known Activations