© 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. 4-RES-JB
    11. 3985
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of the word "hawks"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hawks or hawkish attitudes, particularly in political contexts

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

    No Comments

    Negative Logits
     Annotations
    -0.73
     Mysteries
    -0.72
    ALLY
    -0.71
     Incarnation
    -0.71
     Mankind
    -0.69
     Scotia
    -0.68
    URE
    -0.68
     Winchester
    -0.67
     Result
    -0.67
    LESS
    -0.66
    POSITIVE LOGITS
    keye
    1.35
     haw
    1.33
    kish
    1.19
     hawk
    1.08
    aii
    1.05
    keyes
    1.00
    acles
    0.88
    hawk
    0.88
    ala
    0.85
    wat
    0.83
    Activations Density 0.017%

    No Known Activations