© 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. 4-RES-JB
    11. 7303
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict and opposition

    oai_token-act-pair · gpt-3.5-turbo

    the term "enemies" and related concepts

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

    No Comments

    Negative Logits
    Ħ¢
    -0.80
    printed
    -0.79
    oret
    -0.74
    oard
    -0.72
    option
    -0.68
    electric
    -0.68
     Loch
    -0.66
    oled
    -0.66
    razil
    -0.65
    authorized
    -0.65
    POSITIVE LOGITS
     foe
    1.07
     Enemy
    1.01
    hip
    0.97
     Enemies
    0.94
     adversaries
    0.92
     foes
    0.91
     enemy
    0.90
     enemies
    0.90
     undermin
    0.86
     vanquished
    0.83
    Activations Density 0.024%

    No Known Activations