© 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. 0-RES-JB
    11. 7862
    Prev
    Next
    INDEX
    Explanations

    phrases related to targeting a specific entity or objective

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "targeting" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Guinness
    -0.77
     Glac
    -0.74
    rose
    -0.73
    pole
    -0.72
    erness
    -0.71
    iu
    -0.70
    cup
    -0.69
     Twain
    -0.66
     Cups
    -0.66
    Reviewer
    -0.65
    POSITIVE LOGITS
     targeting
    3.73
     targeted
    2.15
    target
    2.03
     targets
    1.80
     target
    1.80
     aiming
    1.79
     Target
    1.62
    Target
    1.60
     profiling
    1.58
     focusing
    1.41
    Activations Density 0.017%

    No Known Activations