© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 5769
    Prev
    Next
    INDEX
    Explanations

    words related to aggression

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "aggressive" and related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.87
    owship
    -0.85
    psons
    -0.81
    ãĤ´ãĥ³
    -0.79
    udder
    -0.79
    obyl
    -0.74
    FORE
    -0.72
    bare
    -0.71
    frey
    -0.70
    ectar
    -0.70
    POSITIVE LOGITS
     behav
    0.89
     posture
    0.88
     toward
    0.86
     behavior
    0.84
     aggressive
    0.84
     tactics
    0.84
     stance
    0.83
     tendencies
    0.83
     towards
    0.82
     behaviour
    0.80
    Activations Density 0.088%

    No Known Activations