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. 13950
    Prev
    Next
    INDEX
    Explanations

    intense and impactful words and phrases related to conflict, control, and power

    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
    233
    +0.09
    0.2%
    1598
    +0.08
    0.2%
    1314
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    233
    +0.09
    0.06
    914
    +0.08
    0.03
    1431
    +0.08
    0.06
    Negative Logits
     „,
    -0.72
     vnd
    -0.70
     Strukt
    -0.67
     aen
    -0.67
     §.
    -0.66
     coö
    -0.66
     gmbh
    -0.65
     Schrö
    -0.64
     fte
    -0.64
     fath
    -0.64
    POSITIVE LOGITS
     ever
    1.09
     imaginable
    1.01
     EVER
    0.94
    EVER
    0.83
    ever
    0.81
     jamás
    0.74
     ooit
    0.71
     jamais
    0.69
     Ever
    0.69
    Ever
    0.67
    Activations Density 0.419%

    No Known Activations