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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-RES-JB
    6. 273
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to the business practice of outsourcing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "outsourcing" and related terms

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

    No Comments

    Negative Logits
     crest
    -0.76
    icans
    -0.75
    _-
    -0.72
    bian
    -0.70
     Peb
    -0.68
    ican
    -0.68
    arters
    -0.67
    FK
    -0.66
    Interstitial
    -0.66
    theless
    -0.65
    POSITIVE LOGITS
     outsourcing
    1.42
     Outs
    0.77
     worker
    0.77
     workers
    0.72
    unic
    0.71
     subcontract
    0.69
     Workers
    0.68
    housing
    0.68
    urance
    0.67
     abroad
    0.67
    Activations Density 0.017%

    No Known Activations