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. 433
    Prev
    Next
    INDEX
    Explanations

    terms related to improvements or advancements

    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
    619
    +0.07
    0.2%
    284
    +0.07
    0.2%
    1120
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.07
    0.07
    2030
    +0.07
    0.03
    74
    +0.07
    0.03
    Negative Logits
     fta
    -1.87
     mef
    -1.72
     fte
    -1.66
     fep
    -1.66
     volunte
    -1.65
     fup
    -1.64
     „,
    -1.63
     aen
    -1.63
     thut
    -1.62
     pessi
    -1.61
    POSITIVE LOGITS
    <bos>
    0.99
     onto
    0.78
    ftagPool
    0.70
     into
    0.70
    blurRadius
    0.68
     towards
    0.61
    ocats
    0.60
     against
    0.60
     unto
    0.59
    leyebilirsiniz
    0.59
    Activations Density 0.353%

    No Known Activations