© 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. 10745
    Prev
    Next
    INDEX
    Explanations

    expressions related to emotions or personal experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gladness and self-reflection on personal issues

    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
    ensibly
    -0.80
     outset
    -0.77
     Flavoring
    -0.74
    Indeed
    -0.71
    Certainly
    -0.71
    particularly
    -0.70
     markedly
    -0.69
    iosyncr
    -0.69
    Nevertheless
    -0.69
    onding
    -0.68
    POSITIVE LOGITS
     THEY
    1.27
     ya
    1.23
     you
    1.23
     YOU
    1.15
     we
    1.09
     they
    1.09
     I
    1.07
     she
    1.05
     SHE
    1.05
     thou
    1.00
    Activations Density 0.622%

    No Known Activations