© 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. 2835
    Prev
    Next
    INDEX
    Explanations

    adjectives related to superiority or high quality

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "highly" and its variants, often indicating strong emphasis or quality

    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
    heny
    -0.70
     Rite
    -0.68
    ovie
    -0.67
    okia
    -0.66
    lins
    -0.66
    psons
    -0.66
     Dare
    -0.65
    osaurs
    -0.64
    busters
    -0.64
     blindness
    -0.63
    POSITIVE LOGITS
     regarded
    1.08
     educated
    0.99
     rated
    0.98
     unlikely
    0.98
     anticipated
    0.95
     publicized
    0.91
     improbable
    0.90
     prized
    0.89
     valued
    0.88
     skilled
    0.87
    Activations Density 0.031%

    No Known Activations