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. 15706
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory language related to discrimination and constitutional rights

    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
    1343
    +0.21
    0.6%
    1150
    +0.16
    0.5%
    382
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.21
    0.05
    1343
    +0.16
    0.05
    499
    +0.14
    0.04
    Negative Logits
     snippetHide
    -0.60
    Cześć
    -0.58
    @[+][
    -0.56
    ഉ
    -0.55
    Hogyan
    -0.54
     smtplib
    -0.54
    تحميل
    -0.54
    pří
    -0.54
    gelopen
    -0.53
    RefNanny
    -0.53
    POSITIVE LOGITS
     labd
    0.81
     disagre
    0.78
     practition
    0.76
     coö
    0.76
     impractica
    0.76
     effe
    0.74
     lele
    0.73
     Incenti
    0.73
     fatis
    0.72
     impra
    0.72
    Activations Density 0.226%

    No Known Activations