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. 168
    Prev
    Next
    INDEX
    Explanations

    references to organizations and entities involved in environmental or social activism

    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
    184
    +0.33
    1.2%
    50
    +0.20
    0.7%
    453
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.33
    0.07
    184
    +0.20
    0.02
    1884
    +0.12
    0.05
    Negative Logits
    <bos>
    -2.77
    intios
    -0.76
    Vidite
    -0.68
    .
    -0.66
    ↵↵
    -0.64
    Aholisi
    -0.64
    (
    -0.63
     Dizziness
    -0.62
    ,
    -0.62
    ///**
    -0.62
    POSITIVE LOGITS
     saar
    1.88
     maksi
    1.85
     meis
    1.84
     kram
    1.81
     lele
    1.75
     pank
    1.74
     silikon
    1.74
     makro
    1.73
     kaos
    1.72
     kac
    1.70
    Activations Density 0.385%

    No Known Activations