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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 3863
    Prev
    Next
    INDEX
    Explanations

    terms related to mechanical devices or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to mechanical devices and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itia
    -0.77
    ning
    -0.77
    say
    -0.74
    upon
    -0.73
    inoa
    -0.71
    apest
    -0.70
    vier
    -0.70
    ews
    -0.70
    soon
    -0.69
     Retrieved
    -0.69
    POSITIVE LOGITS
     ventilation
    1.06
     engineering
    1.03
     mechanical
    1.02
     keyboards
    0.95
     fracturing
    0.92
     systems
    0.88
     actu
    0.88
     braking
    0.87
     glitches
    0.85
     engineer
    0.85
    Activations Density 0.009%

    No Known Activations