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. 13596
    Prev
    Next
    INDEX
    Explanations

    mentions of "ji" groups, particularly related to extremist activities

    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
    1961
    +0.17
    0.7%
    1276
    +0.15
    0.6%
    144
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    144
    +0.17
    0.02
    1637
    +0.15
    0.02
    1276
    +0.13
    0.02
    Negative Logits
    ValueGeneration
    -0.56
    Дереккөздер
    -0.56
    د
    -0.54
    Após
    -0.54
    ROGEN
    -0.53
    TargetException
    -0.53
    CloseOperation
    -0.53
    DrawerToggle
    -0.52
    هذا
    -0.52
     Oregon
    -0.52
    POSITIVE LOGITS
     increa
    1.61
     embra
    1.59
     emphat
    1.58
     suscep
    1.57
     pessi
    1.54
     maneu
    1.51
     inev
    1.49
     reluct
    1.49
     strick
    1.48
     intermitt
    1.48
    Activations Density 0.142%

    No Known Activations