© 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. 10-RES-JB
    11. 13947
    Prev
    Next
    INDEX
    Explanations

    technical terms related to missile technology

    oai_token-act-pair · gpt-3.5-turbo

    references to missile capabilities and threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.81
     Journals
    -0.80
     Fiona
    -0.80
     Franchise
    -0.80
     âĶľ
    -0.79
     Volunte
    -0.77
     Equality
    -0.76
     Salary
    -0.75
     Restaur
    -0.74
     Fellowship
    -0.73
    POSITIVE LOGITS
     warheads
    1.81
     missiles
    1.76
     deton
    1.76
     missile
    1.72
     detonated
    1.53
     munitions
    1.51
     Missile
    1.50
     bombs
    1.50
     explosives
    1.45
     ballistic
    1.43
    Activations Density 0.419%

    No Known Activations