© 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. 3-RES-JB
    11. 10684
    Prev
    Next
    INDEX
    Explanations

    words related to drag racing or situations involving resistance or bearing weight

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "drag" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vironment
    -0.86
     AVG
    -0.85
     Kubrick
    -0.73
     Blueprint
    -0.71
     Holmes
    -0.68
     Ramadan
    -0.66
     htt
    -0.64
    VERTISEMENT
    -0.64
    Early
    -0.62
    aples
    -0.62
    POSITIVE LOGITS
     queens
    1.07
     drag
    0.99
    glers
    0.98
    oon
    0.97
     Drag
    0.92
    Drag
    0.88
    ged
    0.85
    orge
    0.82
    hett
    0.82
    wheel
    0.81
    Activations Density 0.009%

    No Known Activations