© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 15683
    Prev
    Next
    INDEX
    Explanations

    mentions of products being manufactured by specific companies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the process of manufacturing and production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Annotations
    -0.75
    ees
    -0.74
    onge
    -0.74
    ward
    -0.72
    unders
    -0.71
    iris
    -0.70
    azing
    -0.66
    frog
    -0.64
    ATH
    -0.63
    mma
    -0.63
    POSITIVE LOGITS
     manufactured
    3.49
    manufact
    1.97
     fabricated
    1.94
     manufactures
    1.84
     Manufact
    1.83
     manufacture
    1.80
     marketed
    1.67
    Manufact
    1.62
     manufact
    1.49
     invented
    1.44
    Activations Density 0.018%

    No Known Activations