© 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. 6-RES-JB
    11. 16825
    Prev
    Next
    INDEX
    Explanations

    mentions of a particular individual named "Kid" with varying activation strengths

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Kid" as it relates to specific individuals or contexts

    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
    ãĥ¼ãĥĨãĤ£
    -0.78
     commission
    -0.72
    aukee
    -0.70
     weekday
    -0.68
     confir
    -0.66
     merge
    -0.65
     coalition
    -0.64
     ministers
    -0.63
     fuse
    -0.63
     timestamp
    -0.63
    POSITIVE LOGITS
     Icar
    1.12
    neys
    1.08
    ney
    0.98
    bean
    0.93
     Doodle
    0.90
    amac
    0.88
    Kid
    0.87
    sie
    0.87
    stones
    0.85
    pad
    0.83
    Activations Density 0.028%

    No Known Activations