Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 754
    Prev
    Next
    INDEX
    Explanations

    references to the term "current" 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
    +0.30
    1.7%
    2011
    +0.11
    0.6%
    479
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.30
    0.04
    1942
    +0.11
    0.03
    200
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.99
    ⓧ
    -0.62
    ///**
    -0.61
    //{
    -0.59
    Havolalar
    -0.59
    namespace
    -0.59
     adopt
    -0.59
    define
    -0.58
    activate
    -0.58
    Ligações
    -0.57
    POSITIVE LOGITS
     affor
    1.70
     Juf
    1.56
     accla
    1.54
     fta
    1.51
     maneu
    1.49
     reluct
    1.46
     Intere
    1.46
     aen
    1.46
     ftu
    1.45
     milf
    1.44
    Activations Density 0.040%

    No Known Activations