Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2713
    Prev
    Next
    INDEX
    Explanations

    Italian words and names, possibly related to a specific context or topic

    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
    304
    +0.11
    0.3%
    783
    +0.09
    0.3%
    1589
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.11
    0.07
    981
    +0.09
    0.06
    304
    +0.09
    0.01
    Negative Logits
     Ottobre
    -1.99
     Settembre
    -1.79
     Luglio
    -1.67
     Giugno
    -1.62
     predecess
    -1.56
     costumi
    -1.43
     paradiso
    -1.40
     popoli
    -1.40
     dott
    -1.37
     fuo
    -1.37
    POSITIVE LOGITS
     fta
    1.71
     ftu
    1.70
     fto
    1.66
     vns
    1.60
     aen
    1.58
     tew
    1.56
     fup
    1.56
     tranf
    1.54
     ftre
    1.53
     reft
    1.46
    Activations Density 0.341%

    No Known Activations