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. 7860
    Prev
    Next
    INDEX
    Explanations

    references to baked goods and their preparation

    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
    +0.32
    1.1%
    736
    +0.09
    0.3%
    394
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.32
    0.12
    823
    +0.09
    0.06
    394
    +0.09
    0.08
    Negative Logits
    <bos>
    -1.56
    /***
    
    -0.98
    ⓧ
    -0.95
     meras
    -0.93
     ideolog
    -0.91
     solidar
    -0.90
    ///**
    -0.88
     ló
    -0.87
     pól
    -0.84
     dras
    -0.81
    POSITIVE LOGITS
     shenan
    1.17
     indestru
    1.15
     maneu
    1.10
     reluct
    1.02
     fortn
    0.94
     disagre
    0.93
     apprehen
    0.92
     gaily
    0.91
     wherea
    0.91
     Middles
    0.90
    Activations Density 1.153%

    No Known Activations