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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1675
    Prev
    Next
    INDEX
    Explanations

    information related to financial services such as loans, financing programs, and payment plans

    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
    1553
    +0.20
    0.6%
    1445
    +0.10
    0.3%
    394
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1553
    +0.20
    0.08
    1858
    +0.10
    0.02
    1531
    +0.08
    0.03
    Negative Logits
     inev
    -1.09
     guarante
    -1.08
     compen
    -0.98
     volunte
    -0.97
     unden
    -0.97
     increa
    -0.96
     uniqu
    -0.96
     strick
    -0.96
     effe
    -0.95
     uninten
    -0.93
    POSITIVE LOGITS
     loans
    0.77
     debt
    0.77
     loan
    0.76
     mortgage
    0.72
     lenders
    0.71
     credit
    0.71
     borrowers
    0.70
    loans
    0.66
     lender
    0.66
     repayment
    0.65
    Activations Density 0.356%

    No Known Activations