© 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 · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14785
    Prev
    Next
    INDEX
    Explanations

    mentions of financial institutions, particularly banks

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    197
    +0.15
    0.6%
    1562
    +0.15
    0.6%
    1376
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1562
    +0.15
    0.04
    1376
    +0.15
    0.04
    197
    +0.15
    0.04
    Negative Logits
     daz
    -0.65
     vern
    -0.65
     overla
    -0.64
     dora
    -0.64
     purcha
    -0.62
     guarante
    -0.62
     alre
    -0.62
     zimmer
    -0.61
     ofre
    -0.60
     noel
    -0.60
    POSITIVE LOGITS
     bank
    1.49
    bank
    1.37
     Bank
    1.33
     banks
    1.31
    Bank
    1.26
     BANK
    1.20
     banking
    1.16
     Banks
    1.16
    BANK
    1.16
    banks
    1.15
    Activations Density 0.074%

    No Known Activations