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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20350
    Prev
    Next
    INDEX
    Explanations

    words related to military actions, such as airstrikes and targets

    oai_token-act-pair · gpt-3.5-turbo

    terms related to military airstrikes and their impacts

    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
    Craft
    -0.84
    zek
    -0.78
    vation
    -0.78
    coin
    -0.74
    ãĤ´ãĥ³
    -0.74
    Created
    -0.74
    ĸļ
    -0.72
    ¢
    -0.72
    gebra
    -0.71
    drawn
    -0.71
    POSITIVE LOGITS
     targets
    1.17
     Gaza
    1.12
     insurgents
    1.10
     Houth
    1.07
     rebel
    1.04
     Libya
    1.04
     Syria
    1.02
     civilians
    1.01
     ISIL
    1.01
     enemy
    1.01
    Activations Density 0.164%

    No Known Activations