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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15917
    Prev
    Next
    INDEX
    Explanations

    information related to fundraising and financial contributions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1150
    +0.14
    0.4%
    453
    +0.12
    0.4%
    270
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1965
    +0.14
    0.05
    270
    +0.12
    0.05
    1456
    +0.11
    0.04
    Negative Logits
     éc
    -0.58
     nuage
    -0.57
     vieill
    -0.55
     permett
    -0.54
     renfer
    -0.53
    comuna
    -0.51
    glMatrixMode
    -0.51
     loup
    -0.49
     soprav
    -0.49
     rocher
    -0.47
    POSITIVE LOGITS
     donation
    0.66
     contribution
    0.65
     donations
    0.64
     contributions
    0.62
     donate
    0.61
     donated
    0.60
     amounts
    0.60
    contribution
    0.58
     contributed
    0.58
     Amounts
    0.56
    Activations Density 0.332%

    No Known Activations