© 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. 8-RES-JB
    11. 7788
    Prev
    Next
    INDEX
    Explanations

    contractions with "I am" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal sentiment or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     membr
    -0.74
     occurs
    -0.71
     Reduce
    -0.67
     mater
    -0.65
     Ensure
    -0.65
     emerges
    -0.64
     derives
    -0.64
     meets
    -0.64
     entails
    -0.63
     lasts
    -0.63
    POSITIVE LOGITS
     glad
    1.35
     gonna
    1.23
     thankful
    1.20
     hoping
    1.20
     sorry
    1.15
     guessing
    1.15
     grateful
    1.10
     afraid
    1.07
     sure
    1.04
     proud
    1.02
    Activations Density 0.097%

    No Known Activations