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. 7-RES-JB
    6. 6132
    Prev
    Next
    INDEX
    Explanations

    terms related to industries like aerospace, automotive, semiconductors, and telecommunications

    oai_token-act-pair · gpt-3.5-turbo

    instances of different industrial sectors like aerospace, automotive, and telecommunications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    steen
    -0.99
    Bird
    -0.80
    orah
    -0.80
    bah
    -0.80
    ched
    -0.78
    ilts
    -0.78
    heimer
    -0.77
    abee
    -0.77
    gs
    -0.77
    chery
    -0.76
    POSITIVE LOGITS
     industry
    1.30
     conglomer
    1.11
     industries
    1.07
     firms
    1.07
     conglomerate
    1.07
     sector
    1.03
     mogul
    1.02
     magn
    1.02
     companies
    1.00
     giants
    1.00
    Activations Density 0.097%

    No Known Activations