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. 10-RES-JB
    6. 1828
    Prev
    Next
    INDEX
    Explanations

    instances of the word "from" in various contexts

    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.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.36
    1.7%
    752
    +0.11
    0.5%
    897
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1052
    +0.36
    0.07
    897
    +0.11
    0.06
    331
    +0.10
    0.06
    Negative Logits
    <bos>
    -2.71
    /**
    -0.72
    HideFlags
    -0.69
    /**
    
    -0.69
     invokingState
    -0.68
      
    -0.67
       
    -0.67
    /**
    -0.67
     drive
    -0.67
     also
    -0.65
    POSITIVE LOGITS
     reluct
    1.99
     affor
    1.96
     accla
    1.95
     Juf
    1.92
     unlaw
    1.88
     Khart
    1.86
     impra
    1.86
     increa
    1.83
     Gorb
    1.81
     unwarran
    1.78
    Activations Density 0.220%

    No Known Activations