© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1345
    Prev
    Next
    INDEX
    Explanations

    mentions of financial institutions, particularly banks

    oai_token-act-pair · gpt-3.5-turbo

    references to banks and banking institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ging
    -0.74
     Loving
    -0.72
    mble
    -0.71
    Hunt
    -0.71
    imens
    -0.68
    VID
    -0.64
     USAF
    -0.62
    ttes
    -0.62
    Ùħ
    -0.62
    witz
    -0.61
    POSITIVE LOGITS
    rolled
    1.19
    notes
    1.18
    rupt
    1.17
    note
    1.08
    roller
    1.07
    rollers
    1.06
    roll
    1.03
    rolling
    0.99
     robber
    0.96
     ATM
    0.96
    Activations Density 0.043%

    No Known Activations