© 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. 6-RES-JB
    11. 12790
    Prev
    Next
    INDEX
    Explanations

    damage-related terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to physical damage or harm

    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
    zsche
    -0.87
    zee
    -0.76
    rams
    -0.70
    uesday
    -0.66
    zbek
    -0.64
    KER
    -0.62
     Reloaded
    -0.62
    liner
    -0.62
    anamo
    -0.62
    unin
    -0.61
    POSITIVE LOGITS
     inflicted
    1.13
     mitigation
    0.95
     wrought
    0.95
     damage
    0.94
    damage
    0.82
     damaged
    0.79
     incurred
    0.76
     caused
    0.76
     sustained
    0.76
     havoc
    0.75
    Activations Density 0.031%

    No Known Activations