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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12933
    Prev
    Next
    INDEX
    Explanations

    words related to various hazards, especially workplace hazards

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hazards and safety risks

    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
    ebus
    -0.96
    gdala
    -0.92
    het
    -0.85
    itton
    -0.85
    ampires
    -0.83
    artney
    -0.81
    ivia
    -0.80
    inyl
    -0.80
    ulet
    -0.79
    inx
    -0.76
    POSITIVE LOGITS
     hazard
    1.16
     hazards
    1.11
    ously
    0.92
     mitigation
    0.88
     Hazard
    0.74
    hog
    0.72
     advis
    0.70
    saf
    0.68
     unbeliev
    0.67
     endanger
    0.67
    Activations Density 0.012%

    No Known Activations