© 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. 2-RES-JB
    11. 4421
    Prev
    Next
    INDEX
    Explanations

    words related to targeting or being targeted

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "targeted."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    batch
    -0.73
    thus
    -0.71
    sen
    -0.70
    fo
    -0.69
    Import
    -0.69
    SourceFile
    -0.69
    standing
    -0.66
    aug
    -0.66
    cess
    -0.65
    ETF
    -0.64
    POSITIVE LOGITS
     targeted
    1.10
     targets
    1.08
     targeting
    1.07
     target
    0.90
    oided
    0.88
     prey
    0.86
     killings
    0.84
     squarely
    0.77
     ads
    0.76
    target
    0.75
    Activations Density 0.014%

    No Known Activations