© 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. 1-RES-JB
    11. 10448
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent acts or crimes

    oai_token-act-pair · gpt-3.5-turbo

    references to violent acts, particularly killings and murders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cola
    -0.87
    Stud
    -0.72
    amina
    -0.70
    aque
    -0.70
    Radio
    -0.67
     Tire
    -0.66
    Student
    -0.65
     Plex
    -0.63
    ais
    -0.63
    Jer
    -0.62
    POSITIVE LOGITS
     killings
    1.14
     murders
    1.04
     shootings
    0.99
     spree
    0.98
     homicides
    0.98
    poons
    0.95
    ongs
    0.89
     slaying
    0.88
     slay
    0.82
     shooting
    0.81
    Activations Density 0.015%

    No Known Activations