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. 16069
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions or procedures

    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
    1602
    +0.08
    0.2%
    1694
    +0.07
    0.2%
    1838
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1602
    +0.08
    0.03
    1838
    +0.07
    0.02
    1031
    +0.07
    0.03
    Negative Logits
     affor
    -1.27
     increa
    -1.17
     strick
    -1.10
     impra
    -1.09
     perfet
    -1.08
     guarante
    -1.08
     encomp
    -1.08
     inev
    -1.07
     gaily
    -1.05
     withal
    -1.04
    POSITIVE LOGITS
     services
    0.69
    services
    0.66
     contributions
    0.55
     participation
    0.49
    честву
    0.49
     servicios
    0.49
     contribution
    0.48
     performance
    0.48
     Paglinawan
    0.48
    救命
    0.47
    Activations Density 0.264%

    No Known Activations