© 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. 13531
    Prev
    Next
    INDEX
    Explanations

    proper abbreviations and acronyms

    oai_token-act-pair · gpt-3.5-turbo

    references to the abbreviation "BA," which likely stands for a specific organization or term

    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
    ively
    -0.89
    atures
    -0.89
    ivities
    -0.82
    ittal
    -0.82
    iveness
    -0.76
    naires
    -0.74
    los
    -0.72
    ivity
    -0.72
    aire
    -0.70
    ostics
    -0.70
    POSITIVE LOGITS
    BIP
    1.42
    EGIN
    0.91
    BA
    0.90
    keley
    0.89
    BILITIES
    0.88
    KER
    0.88
    BLE
    0.82
    asketball
    0.80
    BILITY
    0.80
    HAHAHAHA
    0.77
    Activations Density 0.030%

    No Known Activations