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. 15484
    Prev
    Next
    INDEX
    Explanations

    descriptions of colors and textures, especially related to food or drinks

    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
    674
    +0.22
    0.7%
    2034
    +0.12
    0.4%
    297
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.22
    0.09
    1013
    +0.12
    0.09
    2044
    +0.12
    0.08
    Negative Logits
     sappi
    -1.73
     sergio
    -1.43
     roberto
    -1.37
     alberto
    -1.36
     affez
    -1.34
     javier
    -1.33
     parteci
    -1.33
     scopri
    -1.33
     felipe
    -1.31
     jorge
    -1.31
    POSITIVE LOGITS
     and
    0.95
     và
    0.83
     и
    0.81
    ,
    0.80
     while
    0.72
    이고
    0.70
     &&
    0.70
    and
    0.70
    ;
    0.69
     و
    0.68
    Activations Density 0.718%

    No Known Activations