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. 8-RES-JB
    6. 6183
    Prev
    Next
    INDEX
    Explanations

    Phrases related to CNC machining or manufacturing processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to manufacturing and production processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leep
    -0.77
    isSpecialOrderable
    -0.71
     Span
    -0.68
     Byrne
    -0.68
     Mandela
    -0.68
    izoph
    -0.68
    overe
    -0.67
     Gallagher
    -0.66
     epile
    -0.66
     Torrent
    -0.66
    POSITIVE LOGITS
     manufactures
    1.10
     artisan
    1.10
     manufacturing
    1.09
     manufacture
    1.08
    Craft
    1.05
     Manufact
    1.05
     crafts
    1.05
     manufact
    1.04
     fabrication
    1.02
    smanship
    1.01
    Activations Density 0.399%

    No Known Activations