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. 15883
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial investments and transactions

    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
    120
    +0.12
    0.4%
    1177
    +0.11
    0.3%
    1407
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.12
    0.07
    120
    +0.11
    0.05
    481
    +0.09
    0.05
    Negative Logits
    <bos>
    -1.05
    farwyddwr
    -0.70
     Audiodateien
    -0.65
     допомогти
    -0.61
    бливості
    -0.60
     грудня
    -0.59
     використо
    -0.59
     العزيز
    -0.59
     يوليو
    -0.58
     умова
    -0.58
    POSITIVE LOGITS
     reluct
    1.66
     impra
    1.66
     increa
    1.64
     maneu
    1.63
     encomp
    1.60
     affor
    1.59
     suscep
    1.58
     disreg
    1.55
     depic
    1.55
     accla
    1.55
    Activations Density 0.453%

    No Known Activations