© 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. 6-RES-JB
    11. 20733
    Prev
    Next
    INDEX
    Explanations

    phrases related to a state or action about to happen

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a state of being on the verge or brink of a significant event or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ials
    -0.86
    hee
    -0.73
    til
    -0.73
    cause
    -0.71
    ially
    -0.68
     directs
    -0.68
    uristic
    -0.68
    isms
    -0.67
    ets
    -0.66
    net
    -0.66
    POSITIVE LOGITS
     relegation
    0.98
     bankruptcy
    0.93
     infancy
    0.93
     puberty
    0.92
     extinction
    0.87
    uberty
    0.84
     completion
    0.82
     brink
    0.82
     renaissance
    0.81
     relapse
    0.80
    Activations Density 0.159%

    No Known Activations