© 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. 7-RES-JB
    11. 23602
    Prev
    Next
    INDEX
    Explanations

    phrases or acronyms related to the term "NA"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "NA," indicating a focus on North American contexts or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nuts
    -0.85
    lift
    -0.77
    tons
    -0.76
    ienced
    -0.76
    loo
    -0.75
    notes
    -0.73
    bats
    -0.71
    starter
    -0.70
    enery
    -0.70
    birds
    -0.69
    POSITIVE LOGITS
    ZI
    1.30
    ACP
    1.20
    WAYS
    1.00
    WD
    0.98
    FU
    0.96
    BLE
    0.94
    BER
    0.94
    VAL
    0.92
    IRO
    0.92
    UT
    0.92
    Activations Density 0.030%

    No Known Activations