© 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. 12546
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms starting with "SN"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific channels or media identifiers

    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
    inventoryQuantity
    -0.70
     Kali
    -0.68
     Weinstein
    -0.66
     Duchess
    -0.66
     Reincarnated
    -0.65
     Emir
    -0.63
     Gemini
    -0.62
     NCT
    -0.62
    reon
    -0.62
     Newport
    -0.61
    POSITIVE LOGITS
    SN
    1.23
    ASH
    1.00
    OW
    0.89
    KR
    0.87
    BOOK
    0.86
    ACK
    0.86
    IFF
    0.84
    TY
    0.78
    urring
    0.78
    azer
    0.78
    Activations Density 0.005%

    No Known Activations