© 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. 2-RES-JB
    11. 17299
    Prev
    Next
    INDEX
    Explanations

    words related to violent actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to violent crime

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heit
    -0.87
    printed
    -0.82
    ocular
    -0.78
    alg
    -0.78
    urion
    -0.73
    acl
    -0.73
    ayers
    -0.72
    swer
    -0.72
    omo
    -0.71
    obyl
    -0.71
    POSITIVE LOGITS
     violence
    1.01
     violent
    0.97
     offenders
    0.90
     thugs
    0.87
     gang
    0.87
     gangs
    0.86
     Islamist
    0.84
     assault
    0.83
     aggression
    0.83
     extremism
    0.82
    Activations Density 0.018%

    No Known Activations