© 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. 3-RES-JB
    11. 6145
    Prev
    Next
    INDEX
    Explanations

    proper nouns or abbreviations related to financial institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to JP Morgan and related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thirds
    -0.83
    rights
    -0.81
    rums
    -0.78
    rum
    -0.73
    teenth
    -0.72
    staking
    -0.71
    querque
    -0.70
    leneck
    -0.70
     Rebels
    -0.70
     Masquerade
    -0.64
    POSITIVE LOGITS
    JP
    1.19
    UNE
    0.96
    TAG
    0.92
    avascript
    0.92
    NI
    0.92
    oint
    0.92
    KR
    0.92
    EG
    0.92
    NL
    0.90
    PG
    0.90
    Activations Density 0.009%

    No Known Activations