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. 8403
    Prev
    Next
    INDEX
    Explanations

    information related to various incidents and news events, potentially focusing on violence and safety concerns

    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
    2019
    +0.17
    0.5%
    1535
    +0.16
    0.5%
    2034
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1535
    +0.17
    0.07
    2019
    +0.16
    0.07
    1730
    +0.12
    0.05
    Negative Logits
     tupperware
    -1.00
     ecru
    -0.94
     camry
    -0.92
     chrysler
    -0.90
     embodi
    -0.87
     Darum
    -0.87
     unlaw
    -0.85
     hairc
    -0.85
     jetta
    -0.85
     cushi
    -0.81
    POSITIVE LOGITS
    These
    0.95
     These
    0.87
    these
    0.85
     these
    0.67
    hese
    0.61
     Theses
    0.60
    IMPORTED
    0.59
    Even
    0.57
     THESE
    0.57
    DoubleQuotes
    0.57
    Activations Density 0.422%

    No Known Activations