© 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. 2-RES-JB
    11. 12605
    Prev
    Next
    INDEX
    Explanations

    phrases and acronyms related to legal entities or processes

    oai_token-act-pair · gpt-3.5-turbo

    references to regulatory agencies and procedures related to animal welfare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mar
    -0.76
    nen
    -0.75
    shire
    -0.75
    shr
    -0.69
    mable
    -0.69
    gro
    -0.69
    rab
    -0.68
    croft
    -0.68
    umar
    -0.68
    so
    -0.68
    POSITIVE LOGITS
    CHAT
    1.09
    ILS
    1.04
    ETA
    1.01
    IRED
    0.92
    IL
    0.84
    IFIC
    0.83
    è¦ļéĨĴ
    0.83
    ICE
    0.81
    BIL
    0.80
    IFIED
    0.78
    Activations Density 0.010%

    No Known Activations