© 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. 15611
    Prev
    Next
    INDEX
    Explanations

    phrases related to awareness or knowledge of information

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating knowledge or awareness of a situation or event

    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
    soever
    -0.89
    quer
    -0.78
    respective
    -0.72
    erer
    -0.70
    archy
    -0.70
    hement
    -0.67
    inois
    -0.67
    ieu
    -0.66
    arters
    -0.64
    ittal
    -0.63
    POSITIVE LOGITS
     impending
    1.07
     wrongdoing
    0.90
     discrepancies
    0.85
     irregularities
    0.83
     inconsistencies
    0.83
     dangers
    0.75
     changes
    0.74
     rumours
    0.73
     delays
    0.73
     pending
    0.73
    Activations Density 0.154%

    No Known Activations