© 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. 10-RES-JB
    11. 10657
    Prev
    Next
    INDEX
    Explanations

    phrases related to awareness or notification

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "of" in relation to various subjects and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.85
    quer
    -0.76
    erer
    -0.75
    ontent
    -0.73
    isma
    -0.70
    archy
    -0.70
    hesion
    -0.70
    inois
    -0.69
    orld
    -0.66
    UME
    -0.66
    POSITIVE LOGITS
     impending
    1.14
     pending
    0.82
     irregularities
    0.81
     wrongdoing
    0.80
     developments
    0.78
     discrepancies
    0.78
     dangers
    0.78
     rumours
    0.78
     plans
    0.77
     possible
    0.75
    Activations Density 0.168%

    No Known Activations