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. 15825
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of knowledge and 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
    528
    +0.14
    0.5%
    871
    +0.14
    0.5%
    1325
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    871
    +0.14
    0.03
    950
    +0.14
    0.03
    201
    +0.12
    0.01
    Negative Logits
     uhr
    -0.88
     seksi
    -0.84
     Strukt
    -0.82
     saar
    -0.79
     lele
    -0.76
     nomine
    -0.75
     lemp
    -0.75
     magis
    -0.73
     kram
    -0.71
     akut
    -0.70
    POSITIVE LOGITS
     knowledge
    1.34
    knowledge
    1.24
     Knowledge
    1.20
    Knowledge
    1.18
     KNOWLEDGE
    1.03
     knowled
    0.84
     conocimiento
    0.80
    知识
    0.76
    know
    0.75
     knowledgeable
    0.72
    Activations Density 0.083%

    No Known Activations