© 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. 10-RES-JB
    11. 4818
    Prev
    Next
    INDEX
    Explanations

    phrases related to philosophical quotes and sayings

    oai_token-act-pair · gpt-3.5-turbo
    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
     Marketable
    -0.82
     accrued
    -0.79
     arrests
    -0.77
     conversions
    -0.75
     targeted
    -0.74
     protective
    -0.74
     thwarted
    -0.74
     prepar
    -0.73
     complex
    -0.72
     blocks
    -0.71
    POSITIVE LOGITS
    Anonymous
    1.39
    Henry
    1.26
    Doug
    1.24
    Dave
    1.22
    George
    1.22
    eric
    1.19
    Eric
    1.19
    David
    1.19
    Ian
    1.18
    Ron
    1.18
    Activations Density 0.071%

    No Known Activations