© 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. 2-RES-JB
    11. 7226
    Prev
    Next
    INDEX
    Explanations

    phrases denoting a relationship or connection between two entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve the concept of coupling or connection between elements

    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
    emi
    -0.99
    shr
    -0.77
    hov
    -0.74
    acco
    -0.74
    odan
    -0.74
    umer
    -0.71
    cott
    -0.70
    yers
    -0.70
    lus
    -0.68
    metic
    -0.68
    POSITIVE LOGITS
     coupled
    0.91
    tons
    0.74
     coupling
    0.73
     visuals
    0.72
    xual
    0.66
     together
    0.65
     inexper
    0.65
     juxtap
    0.64
     paired
    0.63
     satisf
    0.63
    Activations Density 0.011%

    No Known Activations