© 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. 0-RES-JB
    11. 13961
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to completing various tasks or processes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Com" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LEASE
    -0.72
    stakes
    -0.72
    iera
    -0.66
     stalk
    -0.66
    RH
    -0.64
    sels
    -0.64
    dh
    -0.63
    bott
    -0.63
    irk
    -0.62
     mitigating
    -0.62
    POSITIVE LOGITS
     Com
    3.76
    Com
    2.16
     com
    1.78
     Comm
    1.49
     COM
    1.48
    com
    1.24
    COM
    1.24
     Con
    1.22
     comple
    1.11
    Comm
    1.06
    Activations Density 0.007%

    No Known Activations