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. 3134
    Prev
    Next
    INDEX
    Explanations

    references to specific meals at various locations

    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
    1013
    +0.19
    0.6%
    1870
    +0.10
    0.4%
    1451
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.19
    0.03
    1451
    +0.10
    0.02
    655
    +0.10
    0.02
    Negative Logits
    laquo
    -0.51
    bewerken
    -0.48
     hende
    -0.45
     coq
    -0.44
     autunno
    -0.43
    InputModule
    -0.43
     chèvre
    -0.43
     chanti
    -0.42
    UseVisualStyle
    -0.42
     Juillet
    -0.42
    POSITIVE LOGITS
     dinner
    1.18
    dinner
    1.04
     dinners
    1.02
     Dinner
    1.00
     meal
    1.00
     meals
    0.98
    Dinner
    0.96
     dining
    0.85
     diners
    0.80
     Meal
    0.80
    Activations Density 0.081%

    No Known Activations