© 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. 7-RES-JB
    11. 13345
    Prev
    Next
    INDEX
    Explanations

    words related to aggressive actions, behaviors, and characteristics

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "aggressive" or related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.96
    obyl
    -0.88
    owship
    -0.87
    mbuds
    -0.76
    psons
    -0.74
    FORE
    -0.72
    udder
    -0.70
    ARDIS
    -0.68
    atch
    -0.68
    fab
    -0.67
    POSITIVE LOGITS
     aggressive
    0.93
    ressive
    0.90
     aggressively
    0.86
     posture
    0.85
     stance
    0.81
     toward
    0.80
     tendencies
    0.80
    iveness
    0.80
    aggressive
    0.80
     aggression
    0.79
    Activations Density 0.039%

    No Known Activations