© 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. 7-RES-JB
    11. 23788
    Prev
    Next
    INDEX
    Explanations

    mentions of violent acts, particularly bombings

    oai_token-act-pair · gpt-3.5-turbo

    references to bombing incidents or campaigns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    laus
    -0.93
    videos
    -0.75
    ITY
    -0.72
    learn
    -0.72
    MpServer
    -0.71
    galitarian
    -0.70
    dit
    -0.70
    los
    -0.69
    FINE
    -0.69
    olars
    -0.69
    POSITIVE LOGITS
     bombing
    1.16
     bombings
    0.99
     bomber
    0.96
     raids
    0.95
     spree
    0.89
     barr
    0.89
     bombers
    0.88
     bombard
    0.87
     shelter
    0.83
     shelters
    0.83
    Activations Density 0.024%

    No Known Activations