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

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 4507
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating a direction of opposition

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "opposite."

    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
    atche
    -0.83
    urrent
    -0.80
    ule
    -0.80
    ourn
    -0.78
    zinski
    -0.77
    uay
    -0.77
    gotten
    -0.75
    ashington
    -0.73
    uci
    -0.71
    erest
    -0.70
    POSITIVE LOGITS
     opposite
    0.85
    ICE
    0.79
     sides
    0.78
     oppos
    0.78
    osite
    0.77
     directions
    0.74
     twins
    0.73
     twin
    0.69
     Tend
    0.67
    worldly
    0.66
    Activations Density 0.008%

    No Known Activations