© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4816
    Prev
    Next
    INDEX
    Explanations

    phrases related to various types of accounts, particularly banking and credit accounts

    oai_token-act-pair · gpt-3.5-turbo

    references to bank accounts and related financial terminology

    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
    RAY
    -0.76
    GGGGGGGG
    -0.75
     Sight
    -0.72
    ————
    -0.70
    GGGG
    -0.66
     Hug
    -0.65
     Fang
    -0.65
     wings
    -0.65
    ï¸ı
    -0.64
    NetMessage
    -0.64
    POSITIVE LOGITS
     balances
    1.19
    ancy
    1.18
    abilities
    0.99
     rece
    0.97
     holders
    0.95
    Account
    0.93
     payable
    0.93
    ants
    0.92
     holder
    0.91
    account
    0.91
    Activations Density 0.020%

    No Known Activations