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. 15269
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or individuals such as "Arpaio," "Mohler-Faria," "Nely," "Thorkildsen," and "Concannon."

    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
    1177
    +0.14
    0.5%
    1978
    +0.14
    0.4%
    453
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.14
    0.07
    1001
    +0.14
    0.05
    1177
    +0.13
    0.03
    Negative Logits
    <bos>
    -1.54
    /*---
    -0.61
     وض
    -0.58
    لينكات
    -0.57
     서울
    -0.56
     소녀
    -0.56
     no
    -0.56
     나는
    -0.56
     mamy
    -0.55
     头像
    -0.54
    POSITIVE LOGITS
     Bartholo
    1.60
     deleter
    1.59
     alre
    1.59
     effe
    1.58
     fta
    1.58
     Gorb
    1.56
     Juf
    1.56
     secon
    1.55
     mef
    1.52
     overla
    1.52
    Activations Density 0.231%

    No Known Activations