© 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. 1-RES-JB
    11. 14415
    Prev
    Next
    INDEX
    Explanations

    proper nouns and abbreviations related to computer operating systems

    oai_token-act-pair · gpt-3.5-turbo

    references to operating systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plain
    -0.73
    ãĥ¬
    -0.73
     msec
    -0.71
    ãĥ©ãĥ³
    -0.71
     slee
    -0.67
     instant
    -0.67
    starter
    -0.67
    ãĥ¼ãĥĨ
    -0.67
    TextColor
    -0.66
     Plain
    -0.65
    POSITIVE LOGITS
    OS
    1.24
    ECTION
    0.93
    ystem
    0.89
     ANGEL
    0.89
    SI
    0.88
    OC
    0.88
    leep
    0.86
    DAQ
    0.85
    afety
    0.84
    OME
    0.82
    Activations Density 0.005%

    No Known Activations