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. 343
    Prev
    Next
    INDEX
    Explanations

    terms related to software development and technical changes

    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
    876
    +0.32
    1.1%
    678
    +0.16
    0.5%
    304
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.32
    0.06
    876
    +0.16
    0.00
    1511
    +0.14
    0.01
    Negative Logits
    <bos>
    -1.21
      
    -0.89
    ,
    -0.89
    .
    -0.89
    WebControls
    -0.88
    ))
    -0.88
    ‌
    -0.87
     Moines
    -0.87
    ,”
    -0.86
    ↵↵
    -0.86
    POSITIVE LOGITS
     encomp
    3.11
     wien
    3.10
     increa
    3.10
     squa
    3.08
     guarante
    3.07
     effe
    3.04
     affor
    3.02
     maneu
    2.99
     scrat
    2.98
     inev
    2.97
    Activations Density 0.242%

    No Known Activations