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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5524
    Prev
    Next
    INDEX
    Explanations

    mentions of aggressive behavior or aggression-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to aggressive behaviors and violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FORMATION
    -0.76
    zl
    -0.74
    verend
    -0.74
    HCR
    -0.70
    obook
    -0.68
    lev
    -0.67
     Bake
    -0.67
    ummer
    -0.66
    haul
    -0.65
    aver
    -0.65
    POSITIVE LOGITS
     aggression
    0.89
     against
    0.85
     aggress
    0.82
     towards
    0.82
     toward
    0.79
     posture
    0.78
    iveness
    0.77
     escalation
    0.76
     provocation
    0.76
    Agg
    0.73
    Activations Density 0.053%

    No Known Activations