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. 13947
    Prev
    Next
    INDEX
    Explanations

    terms related to unique abilities and attributes in a gaming context, as well as specific network addressing information

    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
    876
    +0.19
    0.6%
    1177
    +0.14
    0.4%
    1699
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    93
    +0.19
    0.04
    876
    +0.14
    0.00
    981
    +0.13
    0.03
    Negative Logits
    اقرأ
    -0.86
     всичко
    -0.83
    Bibliografía
    -0.83
     Winaray
    -0.82
    הח
    -0.82
    Εκ
    -0.82
    În
    -0.81
    هذا
    -0.81
    لقد
    -0.81
    Filmo
    -0.80
    POSITIVE LOGITS
     ?...
    2.93
     !...
    2.82
     emphat
    2.79
     increa
    2.77
     inconce
    2.70
     deleter
    2.69
     fuf
    2.69
     embra
    2.69
     suscep
    2.64
     suspic
    2.62
    Activations Density 0.093%

    No Known Activations