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. 6-RES-JB
    6. 19347
    Prev
    Next
    INDEX
    Explanations

    references to workers and their conditions in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to workers and labor-related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tet
    -0.70
    olic
    -0.69
    forth
    -0.67
    MENTS
    -0.66
    osp
    -0.66
    âĸ¬
    -0.66
    croft
    -0.65
    laus
    -0.65
    ãĤ¦ãĤ¹
    -0.64
    uncture
    -0.63
    POSITIVE LOGITS
    worker
    0.92
    hops
    0.91
    folk
    0.89
    workers
    0.89
    paces
    0.88
     ants
    0.84
    geist
    0.81
     ethic
    0.79
     unions
    0.78
    wings
    0.78
    Activations Density 0.035%

    No Known Activations