© 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. 7-RES-JB
    11. 20804
    Prev
    Next
    INDEX
    Explanations

    phrases related to unfolding situations or processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to events or situations unfolding over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asus
    -0.87
    cius
    -0.77
    antry
    -0.71
    udi
    -0.68
    shaw
    -0.68
    avorite
    -0.67
    erva
    -0.65
    resents
    -0.64
    oppy
    -0.64
    aints
    -0.64
    POSITIVE LOGITS
    fitted
    0.95
    stretched
    0.87
     differently
    0.85
    wards
    0.85
    casts
    0.80
     loud
    0.79
    posts
    0.76
     exactly
    0.72
    matched
    0.71
    flows
    0.71
    Activations Density 0.060%

    No Known Activations