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. 13570
    Prev
    Next
    INDEX
    Explanations

    technical terms related to agreements and technical documentation

    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
    1842
    +0.26
    0.8%
    1150
    +0.15
    0.5%
    1870
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.26
    0.09
    136
    +0.15
    0.04
    1870
    +0.14
    0.05
    Negative Logits
     négociations
    -0.84
     conç
    -0.82
     gouvernements
    -0.79
     leçons
    -0.79
     juges
    -0.78
     débats
    -0.76
     vérit
    -0.76
     déclarations
    -0.76
     modalités
    -0.75
     bénéfices
    -0.75
    POSITIVE LOGITS
     ducato
    0.61
     lupo
    0.61
     sentra
    0.60
     specchio
    0.59
     fides
    0.59
     חיצוניים
    0.59
     bosco
    0.58
    ponses
    0.57
     bandung
    0.56
     lepro
    0.56
    Activations Density 0.789%

    No Known Activations