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. 1579
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial support decisions

    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
    1937
    +0.13
    0.5%
    370
    +0.12
    0.4%
    78
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    370
    +0.13
    0.03
    1937
    +0.12
    0.03
    765
    +0.11
    0.03
    Negative Logits
     Verg
    -0.44
     Simultaneously
    -0.41
     Koning
    -0.41
     Really
    -0.40
    митри
    -0.40
     Schäfer
    -0.39
     Rekord
    -0.39
     subsidi
    -0.38
    cm
    -0.38
     Kand
    -0.38
    POSITIVE LOGITS
     DUE
    1.00
    due
    0.89
    Due
    0.85
     due
    0.81
     Due
    0.80
    DUE
    0.73
     dégust
    0.70
     nephe
    0.69
    comuna
    0.69
     Debido
    0.68
    Activations Density 0.066%

    No Known Activations