© 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. 1-RES-JB
    11. 20077
    Prev
    Next
    INDEX
    Explanations

    terms related to mechanical objects or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to mechanical concepts and devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ning
    -0.82
    soon
    -0.77
    Chance
    -0.73
    rooms
    -0.72
     Innocent
    -0.72
     Retrieved
    -0.72
    say
    -0.71
     Zuckerberg
    -0.71
    kers
    -0.71
    ews
    -0.70
    POSITIVE LOGITS
     mechanical
    1.17
     ventilation
    1.07
     engineering
    1.00
     resil
    0.97
     keyboards
    0.93
     actu
    0.92
     destro
    0.92
     mechanically
    0.91
     typew
    0.89
     glitches
    0.89
    Activations Density 0.012%

    No Known Activations