© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16702
    Prev
    Next
    INDEX
    Explanations

    titles or designations related to high-ranking corporate positions

    oai_token-act-pair · gpt-3.5-turbo

    references to vice president positions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ding
    -0.79
    orkshire
    -0.70
     obser
    -0.69
     towed
    -0.68
    ãĥĥãĤ¯
    -0.67
     sporadic
    -0.66
    MpServer
    -0.64
     magnitude
    -0.63
     tolerate
    -0.62
     hypers
    -0.60
    POSITIVE LOGITS
     VP
    1.04
    VP
    1.01
    olicy
    0.95
    OTUS
    0.94
    VC
    0.93
    IME
    0.79
    iors
    0.77
    ovo
    0.76
     versa
    0.76
    ppe
    0.75
    Activations Density 0.006%

    No Known Activations