© 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. 1583
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Dra" followed by various letters, potentially indicating a specific name or entity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific names or brands related to draught beer

    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
    ancial
    -0.72
    ulators
    -0.65
    LESS
    -0.63
    ulus
    -0.62
    ARC
    -0.61
     ICC
    -0.61
     Hardy
    -0.61
     Beir
    -0.60
     Simulator
    -0.60
    papers
    -0.59
    POSITIVE LOGITS
    ven
    1.23
    ught
    1.20
    fters
    1.14
    ves
    1.09
    ving
    1.03
    ugh
    1.01
    pped
    1.00
    plets
    0.98
    vel
    0.95
    quel
    0.93
    Activations Density 0.035%

    No Known Activations