© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 17186
    Prev
    Next
    INDEX
    Explanations

    terms related to the field of engineering

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "engineering."

    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
    theless
    -0.76
     Cele
    -0.73
    onymous
    -0.71
    tle
    -0.69
    ctuary
    -0.67
     Beir
    -0.67
    holders
    -0.65
     [+
    -0.65
    violent
    -0.65
    etheless
    -0.65
    POSITIVE LOGITS
    Engineers
    0.99
     marvel
    0.93
     engineering
    0.87
    Materials
    0.82
     engineer
    0.81
     engineers
    0.81
    rador
    0.80
     technician
    0.77
    workshop
    0.76
     disciplines
    0.74
    Activations Density 0.039%

    No Known Activations