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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 12-RES-JB
    6. 7858
    Prev
    Next
    INDEX
    Explanations

    the concept of 'means' or methods used to achieve something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.28
    1.3%
    68
    +0.14
    0.7%
    32
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1983
    +0.28
    0.03
    68
    +0.14
    0.03
    1705
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.24
    /***
    
    -0.62
    脊
    -0.62
    public
    -0.61
     restore
    -0.60
    돕
    -0.60
     cu
    -0.58
    protected
    -0.58
     Stu
    -0.58
     Hunter
    -0.57
    POSITIVE LOGITS
     milano
    1.41
     soggior
    1.41
     claudia
    1.38
     paradiso
    1.38
     coar
    1.37
     napoli
    1.35
     pymysql
    1.33
     santiago
    1.33
     affez
    1.31
     jorge
    1.31
    Activations Density 0.043%

    No Known Activations