© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18903
    Prev
    Next
    INDEX
    Explanations

    phrases related to productivity, decision-making, and self-improvement

    oai_token-act-pair · gpt-3.5-turbo

    statements about human behavior and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bernatorial
    -0.74
     Together
    -0.71
    overed
    -0.69
     marqu
    -0.69
     Laure
    -0.68
    tained
    -0.67
     laureate
    -0.67
    tains
    -0.66
    venue
    -0.66
     Sisters
    -0.66
    POSITIVE LOGITS
     resent
    1.46
     unconsciously
    1.39
     subconscious
    1.36
     instinctively
    1.34
     distrust
    1.30
     perceive
    1.27
     mistrust
    1.27
     crave
    1.24
     hesitate
    1.23
     impuls
    1.21
    Activations Density 0.442%

    No Known Activations