Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14036
    Prev
    Next
    INDEX
    Explanations

    mentions of financial institutions and government departments specifically related to treasury

    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
    1334
    +0.14
    0.6%
    991
    +0.14
    0.5%
    1742
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    991
    +0.14
    0.02
    1971
    +0.14
    0.02
    1742
    +0.12
    0.02
    Negative Logits
     gild
    -0.74
     guarante
    -0.73
     fuf
    -0.73
     gaily
    -0.71
     indor
    -0.68
     effe
    -0.68
     reluct
    -0.68
     snoopy
    -0.67
     disagre
    -0.67
     inext
    -0.67
    POSITIVE LOGITS
     Treasury
    1.14
     treasury
    1.00
    Treasury
    0.99
    treas
    0.92
     TREAS
    0.86
     Treas
    0.68
     Treasurer
    0.67
     treasurer
    0.64
     Treasure
    0.60
    Treasurer
    0.56
    Activations Density 0.123%

    No Known Activations