© 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. 10027
    Prev
    Next
    INDEX
    Explanations

    phrases indicating deep contemplation or consideration

    oai_token-act-pair · gpt-3.5-turbo

    statements related to deep contemplation and consideration

    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
    adra
    -0.68
    Availability
    -0.67
    catentry
    -0.66
    reditation
    -0.63
    ufact
    -0.62
    ublic
    -0.60
    orest
    -0.60
    idated
    -0.59
     unsc
    -0.58
    ante
    -0.56
    POSITIVE LOGITS
     aloud
    1.17
     carefully
    0.80
    about
    0.73
     about
    0.72
     beforehand
    0.72
    Hmm
    0.69
     ABOUT
    0.69
     differently
    0.68
    evaluate
    0.68
     unthinkable
    0.66
    Activations Density 0.150%

    No Known Activations