© 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. 9-RES-JB
    11. 4600
    Prev
    Next
    INDEX
    Explanations

    instances where the text refers to qualification, registration, or grouping of people or things

    oai_token-act-pair · gpt-3.5-turbo

    terms related to registration and qualifying processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rought
    -0.59
    hire
    -0.57
    geoning
    -0.56
    thing
    -0.56
    ija
    -0.56
     aggregation
    -0.55
    VA
    -0.55
    ĸļ
    -0.54
    issue
    -0.54
    hoe
    -0.54
    POSITIVE LOGITS
     peacefully
    1.03
     themselves
    0.93
     oneself
    0.87
     accordingly
    0.86
     seamlessly
    0.80
     spontaneously
    0.79
     herself
    0.77
     comfortably
    0.77
     himself
    0.76
     prematurely
    0.75
    Activations Density 0.306%

    No Known Activations