© 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. 0-RES-JB
    11. 1697
    Prev
    Next
    INDEX
    Explanations

    words related to mechanical gears or activities involving a sequence of changes or movements

    oai_token-act-pair · gpt-3.5-turbo

    references to gears or mechanical concepts

    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
    rape
    -0.75
    Ban
    -0.71
     Vera
    -0.70
     McInt
    -0.69
    Interstitial
    -0.68
    arantine
    -0.68
    IDA
    -0.68
    azo
    -0.68
     INF
    -0.67
    tnc
    -0.67
    POSITIVE LOGITS
     gears
    3.49
     gearing
    3.08
     geared
    1.73
     Gears
    1.66
     grind
    1.57
     winding
    1.55
    Gear
    1.48
     gear
    1.44
     grinding
    1.31
    gear
    1.26
    Activations Density 0.047%

    No Known Activations