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

    Neuronpedia

    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. 10-RES-JB
    11. 3031
    Prev
    Next
    INDEX
    Explanations

    text related to discussions about government decisions and proposals

    oai_token-act-pair · gpt-3.5-turbo

    words related to governmental decisions and infrastructure projects

    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
    ĸļ
    -0.84
     Parenthood
    -0.75
     redress
    -0.72
     Serve
    -0.72
     Abuse
    -0.71
     Citation
    -0.70
    icka
    -0.68
     correction
    -0.68
     Occupations
    -0.66
     Breach
    -0.65
    POSITIVE LOGITS
     envision
    1.57
     envis
    1.51
     brainstorm
    1.46
     envisioned
    1.46
     plans
    1.37
     contemplated
    1.35
     dreamed
    1.33
     planning
    1.28
     plan
    1.28
     ambitions
    1.26
    Activations Density 1.415%

    No Known Activations