© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 4667
    Prev
    Next
    INDEX
    Explanations

    instances of physical damage or accidents

    oai_token-act-pair · gpt-3.5-turbo

    events involving injuries or damages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bern
    -0.74
    Companies
    -0.67
    }}}
    -0.66
    icons
    -0.65
    nda
    -0.64
    ocations
    -0.63
    leground
    -0.62
     resumes
    -0.61
    ertain
    -0.60
    Demand
    -0.60
    POSITIVE LOGITS
     accidentally
    1.26
     injuring
    1.16
     unexpectedly
    1.05
     prematurely
    1.04
     tragically
    1.03
     inadvertently
    0.98
     unintentionally
    0.96
     injure
    0.95
     during
    0.93
     violently
    0.90
    Activations Density 0.366%

    No Known Activations