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. 13551
    Prev
    Next
    INDEX
    Explanations

    information related to real estate 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
    1053
    +0.14
    0.5%
    897
    +0.13
    0.5%
    32
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1053
    +0.14
    0.06
    395
    +0.13
    0.06
    2016
    +0.11
    0.06
    Negative Logits
     tanong
    -0.69
     bagay
    -0.67
     sava
    -0.63
     unwarran
    -0.61
     Sequo
    -0.54
     sarili
    -0.53
    XmlEnum
    -0.53
    termilk
    -0.51
    erapeu
    -0.51
     iyong
    -0.50
    POSITIVE LOGITS
     at
    0.79
     At
    0.76
     AT
    0.74
    At
    0.67
     sappi
    0.65
    at
    0.63
     vorrei
    0.63
     purtroppo
    0.60
    atguigu
    0.60
    Ats
    0.58
    Activations Density 0.210%

    No Known Activations