© 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. 22630
    Prev
    Next
    INDEX
    Explanations

    words related to aggressive behavior

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "aggressive" and its variations

    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
    cloth
    -0.81
     Literature
    -0.72
    fell
    -0.70
    tl
    -0.69
     Plato
    -0.69
    umber
    -0.68
    orage
    -0.68
     Medals
    -0.68
     Books
    -0.67
     Libraries
    -0.67
    POSITIVE LOGITS
     aggressive
    3.44
    aggressive
    2.86
     aggressively
    2.14
     aggress
    1.90
     aggression
    1.90
     proactive
    1.65
    Agg
    1.59
     forceful
    1.49
     intrusive
    1.44
     aggro
    1.43
    Activations Density 0.031%

    No Known Activations