© 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. 7-RES-JB
    11. 1465
    Prev
    Next
    INDEX
    Explanations

    adjectives related to seriousness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "serious."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atu
    -0.87
    wright
    -0.85
    enaries
    -0.85
    eez
    -0.75
    Ĥİ
    -0.72
    ucky
    -0.71
    av
    -0.71
    ifully
    -0.70
    orious
    -0.70
    via
    -0.68
    POSITIVE LOGITS
    lly
    0.95
     consideration
    0.87
     serious
    0.84
     contender
    0.81
    serious
    0.80
     enough
    0.77
    nces
    0.74
     understatement
    0.74
     dent
    0.73
    gn
    0.72
    Activations Density 0.031%

    No Known Activations