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. 705
    Prev
    Next
    INDEX
    Explanations

    statements or quotations from people

    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
    1919
    +0.12
    0.4%
    1373
    +0.09
    0.3%
    227
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.12
    0.07
    862
    +0.09
    0.03
    1424
    +0.08
    0.03
    Negative Logits
     lele
    -0.96
     alha
    -0.82
     katun
    -0.82
     jati
    -0.82
     lemp
    -0.78
     susun
    -0.78
     palab
    -0.74
     kela
    -0.74
     seksi
    -0.72
     jawa
    -0.71
    POSITIVE LOGITS
     chrysler
    0.78
     lexus
    0.67
     heapq
    0.62
     pymysql
    0.59
     gladly
    0.59
     shenan
    0.59
     camaro
    0.58
     outlander
    0.56
     hilux
    0.56
     isuzu
    0.56
    Activations Density 0.165%

    No Known Activations