© 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. 6-RES-JB
    11. 1600
    Prev
    Next
    INDEX
    Explanations

    phrases related to targeting or focusing on specific entities or groups for some action or purpose

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "targeting" or related variations indicating focus on specific groups or objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fo
    -0.87
    SourceFile
    -0.75
    batch
    -0.72
    mpeg
    -0.68
    Created
    -0.68
    aut
    -0.67
    iHUD
    -0.67
    aug
    -0.65
    uid
    -0.64
    loo
    -0.64
    POSITIVE LOGITS
     targets
    0.94
     targeting
    0.84
    ted
    0.82
     squarely
    0.80
    ively
    0.74
     target
    0.73
     specificity
    0.71
    eers
    0.68
     civilians
    0.68
     targeted
    0.68
    Activations Density 0.025%

    No Known Activations