© 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. 20682
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing duality or multiple aspects of a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing duality or coexistence

    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
    ugu
    -0.72
    renheit
    -0.67
    uez
    -0.64
     Caption
    -0.64
    Trend
    -0.63
    nect
    -0.62
    \\\\\\\\
    -0.62
    dq
    -0.60
    sburgh
    -0.60
    tions
    -0.59
    POSITIVE LOGITS
     sexes
    1.53
     sides
    1.32
     halves
    1.24
     genders
    1.19
     extremes
    0.78
     ends
    0.76
     coasts
    0.75
     thirds
    0.74
     directions
    0.71
     senses
    0.69
    Activations Density 0.059%

    No Known Activations