© 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. 10690
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'chain' and phrases related to interconnected events or items

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "chain" and related phrases indicating sequences or connections

    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
     "$:/
    -0.83
    sburg
    -0.82
     Niet
    -0.73
    gdala
    -0.72
    orescent
    -0.70
     Gors
    -0.70
    vironment
    -0.70
    iator
    -0.70
    racuse
    -0.70
    farious
    -0.69
    POSITIVE LOGITS
    chain
    0.97
    alysis
    0.95
    mail
    0.91
    Chain
    0.88
    wal
    0.87
    cloth
    0.86
    loader
    0.85
     chain
    0.85
    breaker
    0.84
    params
    0.82
    Activations Density 0.024%

    No Known Activations