Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 2555
    Prev
    Next
    INDEX
    Explanations

    phrases related to workplace hazards and safety assessments

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of 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 @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gdala
    -1.01
    ebus
    -0.93
    ampires
    -0.85
    ivia
    -0.82
    artney
    -0.82
    itton
    -0.81
    inyl
    -0.79
    inx
    -0.78
    hetti
    -0.76
    thood
    -0.74
    POSITIVE LOGITS
    ously
    1.07
     hazards
    1.03
     hazard
    1.01
     mitigation
    0.85
     Hazard
    0.84
    ous
    0.79
    crow
    0.69
    OUS
    0.67
    hog
    0.66
     endanger
    0.65
    Activations Density 0.022%

    No Known Activations