© 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. 10-RES-JB
    11. 3447
    Prev
    Next
    INDEX
    Explanations

    words related to military actions or strategic maneuvers

    oai_token-act-pair · gpt-3.5-turbo

    the word "launch" and its variations, particularly in contexts involving actions related to attacks, offensives, or campaigns

    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
     discharged
    -0.76
     coefficients
    -0.68
    Reason
    -0.67
     deceased
    -0.65
     +/-
    -0.65
     deposited
    -0.64
     afforded
    -0.64
    Ö¼
    -0.63
     UCHIJ
    -0.63
     elapsed
    -0.63
    POSITIVE LOGITS
     crusade
    1.27
     campaign
    1.16
     crackdown
    1.09
    campaign
    1.08
     attack
    1.07
     concerted
    1.06
     tir
    1.05
     blitz
    1.05
     boycott
    1.04
     assault
    1.04
    Activations Density 0.262%

    No Known Activations