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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 4014
    Prev
    Next
    INDEX
    Explanations

    terms related to working overtime

    oai_token-act-pair · gpt-3.5-turbo

    references to overtime work or hours

    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
    ystem
    -0.86
    ydia
    -0.81
    gling
    -0.80
    er
    -0.75
    hyde
    -0.75
    leon
    -0.75
    etsk
    -0.74
    iard
    -0.74
    yon
    -0.73
    sonian
    -0.73
    POSITIVE LOGITS
     clauses
    0.75
     stopp
    0.73
     Dragonbound
    0.70
     curtain
    0.67
     msec
    0.66
     earnings
    0.64
     compensation
    0.64
     payable
    0.63
     hours
    0.62
     duties
    0.62
    Activations Density 0.132%

    No Known Activations