© 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. 14000
    Prev
    Next
    INDEX
    Explanations

    phrases indicating knowledge or awareness

    oai_token-act-pair · gpt-3.5-turbo

    mentions of awareness regarding various subjects

    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
    soever
    -0.89
    Downloadha
    -0.77
    hement
    -0.70
    erer
    -0.69
    respective
    -0.67
    ©¶æ¥µ
    -0.66
    hesion
    -0.65
    quer
    -0.64
    llan
    -0.64
    uld
    -0.63
    POSITIVE LOGITS
     impending
    0.92
     how
    0.81
     what
    0.79
     firsthand
    0.72
     whats
    0.72
     whence
    0.70
     irregularities
    0.70
     nuances
    0.69
     potential
    0.68
     unfolding
    0.68
    Activations Density 0.119%

    No Known Activations