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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 14723
    Prev
    Next
    INDEX
    Explanations

    terms related to conflict, battles, and rivalries

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to conflict and survival situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.86
    ocket
    -0.82
    ourse
    -0.79
    imester
    -0.79
    ondo
    -0.78
    INESS
    -0.77
    arenthood
    -0.77
    daq
    -0.75
    eanor
    -0.75
    ospons
    -0.75
    POSITIVE LOGITS
     natives
    1.51
     thugs
    1.42
     peasants
    1.37
     mercenaries
    1.36
     Arabs
    1.35
     bandits
    1.34
     Germans
    1.31
     invaders
    1.31
     goblins
    1.28
     warriors
    1.27
    Activations Density 0.802%

    No Known Activations