© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 9224
    Prev
    Next
    INDEX
    Explanations

    specific mentions of ammunition

    oai_token-act-pair · gpt-3.5-turbo

    mentions of ammunition and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.91
    nee
    -0.84
    kj
    -0.74
    visible
    -0.73
    TH
    -0.72
    hew
    -0.71
    Kids
    -0.71
    ŃĶ
    -0.71
     Brow
    -0.70
    Scotland
    -0.69
    POSITIVE LOGITS
     ammunition
    1.26
     cartridges
    1.05
     ammo
    1.04
    munition
    1.00
     Ammunition
    0.93
     pellets
    0.88
     flares
    0.86
     fodder
    0.85
    abwe
    0.85
    andise
    0.84
    Activations Density 0.010%

    No Known Activations