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. 16059
    Prev
    Next
    INDEX
    Explanations

    information related to financial compensation, historical settlements, and economic markets

    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
    2034
    +0.21
    0.7%
    382
    +0.20
    0.6%
    1535
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.21
    0.12
    310
    +0.20
    0.07
    1535
    +0.18
    0.08
    Negative Logits
     viciss
    -1.19
     perfon
    -1.13
     dises
    -1.11
     uncin
    -1.02
     magis
    -1.02
     robus
    -1.01
     tranf
    -0.97
     theolog
    -0.97
     suspic
    -0.96
     obf
    -0.96
    POSITIVE LOGITS
     That
    0.79
     This
    0.77
     Therefore
    0.74
     However
    0.73
     But
    0.73
     It
    0.73
    ↵↵
    0.72
     So
    0.71
     And
    0.70
     If
    0.69
    Activations Density 0.502%

    No Known Activations