© 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. 6-RES-JB
    11. 18397
    Prev
    Next
    INDEX
    Explanations

    terms related to synchronization, such as "synonyms" or "unsynchronized."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "syn" in various forms, signaling a focus on terms related to synchronization or associations

    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
    ORED
    -1.01
    aneers
    -0.79
    DERR
    -0.79
    ModLoader
    -0.78
    IVE
    -0.77
     bearer
    -0.75
    sburg
    -0.71
    een
    -0.71
     Eternity
    -0.68
    200000
    -0.68
    POSITIVE LOGITS
    agog
    1.20
    agogue
    1.12
    apse
    1.06
    opsis
    1.03
    apses
    1.02
    onyms
    1.01
    onym
    0.97
    chron
    0.93
    apt
    0.90
    onymous
    0.90
    Activations Density 0.020%

    No Known Activations