© 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. 4-RES-JB
    11. 10512
    Prev
    Next
    INDEX
    Explanations

    mentions of specific credit card types

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Master" in various contexts

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

    No Comments

    Negative Logits
    OPLE
    -0.81
    IDER
    -0.80
    hedon
    -0.71
    irtual
    -0.69
    heres
    -0.64
    IGHTS
    -0.63
    ourcing
    -0.62
    ITCH
    -0.62
    UGE
    -0.61
    enegger
    -0.61
    POSITIVE LOGITS
    piece
    1.23
    mind
    1.17
    pieces
    1.08
    hands
    0.91
     Swordsman
    0.80
    lad
    0.79
    Che
    0.78
    sonian
    0.77
    ington
    0.77
    work
    0.77
    Activations Density 0.010%

    No Known Activations