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. 15376
    Prev
    Next
    INDEX
    Explanations

    mentions of investments and their positive outcomes

    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
    170
    +0.07
    0.2%
    1436
    +0.07
    0.2%
    252
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1193
    +0.07
    0.04
    707
    +0.07
    0.03
    310
    +0.07
    0.02
    Negative Logits
     franz
    -1.03
     gend
    -0.91
     lele
    -0.89
     mef
    -0.89
     bandung
    -0.87
     Departement
    -0.87
     hcm
    -0.86
     gmbh
    -0.85
     wien
    -0.85
     saar
    -0.85
    POSITIVE LOGITS
     resulted
    0.79
     rewarded
    0.77
     paid
    0.72
     result
    0.71
    result
    0.68
     pay
    0.68
     results
    0.68
     pays
    0.65
     succeeded
    0.65
     payoff
    0.64
    Activations Density 0.289%

    No Known Activations