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. 2869
    Prev
    Next
    INDEX
    Explanations

    business and finance-related terms, specifically related to revenue and economic interactions

    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
    1870
    +0.20
    0.6%
    1385
    +0.15
    0.5%
    198
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.20
    0.05
    1860
    +0.15
    0.04
    280
    +0.10
    0.05
    Negative Logits
     unspeak
    -1.02
     gaily
    -0.88
     horrend
    -0.87
     unbear
    -0.82
     shenan
    -0.80
     pensive
    -0.80
     dégâts
    -0.78
     disreg
    -0.78
     réactions
    -0.77
     sculptured
    -0.77
    POSITIVE LOGITS
     sement
    1.24
     utop
    1.23
     manuten
    1.18
     balon
    1.15
     furg
    1.13
     pú
    1.12
     lemp
    1.10
     monaster
    1.10
     asfal
    1.10
     ideolog
    1.10
    Activations Density 0.451%

    No Known Activations