© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 4171
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences where someone is described as being aware of something

    oai_token-act-pair · gpt-3.5-turbo

    references to awareness or knowledge of specific information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.86
    erer
    -0.77
    llan
    -0.75
    quer
    -0.73
    hell
    -0.66
    hement
    -0.64
     Robots
    -0.61
    uably
    -0.60
    uld
    -0.60
     Scor
    -0.59
    POSITIVE LOGITS
     impending
    1.07
     irregularities
    0.90
     dangers
    0.80
     deficiencies
    0.80
     vulnerabilities
    0.79
     anomalies
    0.77
     discrepancies
    0.76
     wrongdoing
    0.76
     what
    0.76
     how
    0.75
    Activations Density 0.151%

    No Known Activations