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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 9340
    Prev
    Next
    INDEX
    Explanations

    words related to a controversial labor practice known as "karoshi," which is linked to excessive work leading to serious health issues or even death

    oai_token-act-pair · gpt-3.5-turbo

    references to specific cultural or ethnic identities

    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
     Moroc
    -0.86
     Accountability
    -0.81
     Own
    -0.81
     Yard
    -0.80
     Weather
    -0.79
     Lot
    -0.77
     Fn
    -0.76
     Heard
    -0.76
     Breed
    -0.76
     Notting
    -0.75
    POSITIVE LOGITS
    ensis
    1.07
    acters
    0.93
    berries
    0.77
    bons
    0.76
    iles
    0.74
    igans
    0.74
    Äĵ
    0.73
    ettes
    0.72
    otic
    0.72
    istics
    0.71
    Activations Density 0.370%

    No Known Activations