© 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. 9-RES-JB
    11. 7349
    Prev
    Next
    INDEX
    Explanations

    phrases related to joining a trend or movement

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irection
    -0.67
    bear
    -0.66
    atically
    -0.66
    afia
    -0.64
    isin
    -0.64
    upon
    -0.63
    cade
    -0.63
     suppose
    -0.63
    thood
    -0.62
    usa
    -0.61
    POSITIVE LOGITS
     heels
    1.14
     bandwagon
    1.10
     shoulders
    1.02
     treadmill
    0.97
     doorstep
    0.95
     ledge
    0.93
     porch
    0.88
     pedest
    0.88
     sidelines
    0.84
     balcony
    0.83
    Activations Density 0.144%

    No Known Activations