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. 607
    Prev
    Next
    INDEX
    Explanations

    names of basketball players and teams

    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
    453
    +0.17
    0.5%
    184
    +0.15
    0.4%
    674
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.17
    0.01
    453
    +0.15
    0.03
    981
    +0.09
    0.02
    Negative Logits
    ьаж
    -0.85
     fays
    -0.82
     reft
    -0.81
     prefent
    -0.78
     ftre
    -0.73
     laft
    -0.71
     tranf
    -0.71
     leaft
    -0.69
     clô
    -0.69
     feveral
    -0.69
    POSITIVE LOGITS
    MemoryWarning
    0.49
    內容簡介
    0.48
     trattano
    0.47
    同上
    0.45
    изнь
    0.44
    viaf
    0.41
    extField
    0.40
    SerializedSize
    0.40
     елның
    0.40
    ूरत
    0.39
    Activations Density 0.065%

    No Known Activations