Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13585
    Prev
    Next
    INDEX
    Explanations

    words related to global issues or controversies, particularly regarding political or social events

    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
    198
    +0.12
    0.4%
    1870
    +0.11
    0.4%
    1616
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    143
    +0.12
    0.03
    1616
    +0.11
    0.03
    240
    +0.10
    0.02
    Negative Logits
    -------
    
    -0.55
    DropColumn
    -0.51
    CWE
    -0.48
    yticks
    -0.48
    "]}
    -0.48
    Dichloropropene
    -0.47
    ahul
    -0.46
    FetchType
    -0.46
    ubakar
    -0.46
    marvin
    -0.46
    POSITIVE LOGITS
     Widely
    0.99
     liberality
    0.95
     unlaw
    0.94
     milf
    0.92
     hairc
    0.92
     pamph
    0.89
     indestru
    0.87
     maneu
    0.87
     embodi
    0.84
     thermomix
    0.84
    Activations Density 0.078%

    No Known Activations