© 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. 3-RES-JB
    11. 21162
    Prev
    Next
    INDEX
    Explanations

    mentions of violent events or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    missions
    -0.81
    odes
    -0.81
    ergy
    -0.80
    arton
    -0.79
    ramer
    -0.76
    sonian
    -0.76
    riad
    -0.75
    ocular
    -0.75
    oplan
    -0.73
    nai
    -0.72
    POSITIVE LOGITS
     violence
    0.93
     perpetrated
    0.90
     suppression
    0.87
     repression
    0.84
     inflicted
    0.82
    fulness
    0.77
    fighting
    0.75
    fully
    0.74
     flared
    0.73
     Violence
    0.73
    Activations Density 0.022%

    No Known Activations