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. 8209
    Prev
    Next
    INDEX
    Explanations

    phrases related to advocacy and pushing for change

    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
    397
    +0.15
    0.5%
    1350
    +0.14
    0.5%
    1993
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.15
    0.04
    1350
    +0.14
    0.04
    1993
    +0.12
    0.04
    Negative Logits
     Irak
    -0.49
     Coupé
    -0.47
     autorytatywna
    -0.47
     Bao
    -0.47
    fficio
    -0.46
     Quinta
    -0.45
     Gallardo
    -0.44
     Hela
    -0.44
    Scénario
    -0.43
     Spart
    -0.43
    POSITIVE LOGITS
     push
    1.35
     pushes
    1.27
     pushing
    1.25
     pushed
    1.25
     Push
    1.24
    push
    1.23
     Pushing
    1.22
    Pushing
    1.21
    Push
    1.14
    pushed
    1.13
    Activations Density 0.075%

    No Known Activations