© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12862
    Prev
    Next
    INDEX
    Explanations

    political campaign-related words and phrases

    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
    678
    +0.08
    0.2%
    81
    +0.08
    0.2%
    1823
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.08
    0.04
    1123
    +0.08
    0.05
    2045
    +0.07
    0.06
    Negative Logits
     regardant
    -0.80
     Février
    -0.79
     unwarran
    -0.75
     noël
    -0.74
     Décembre
    -0.73
     swarovski
    -0.72
     embodi
    -0.71
     malheur
    -0.70
     veau
    -0.69
     prêtre
    -0.69
    POSITIVE LOGITS
     campaign
    0.82
     Demokrat
    0.74
     kamp
    0.73
     republi
    0.70
     Senat
    0.68
     biograf
    0.67
     campaigning
    0.66
     Wiking
    0.65
     Kalifor
    0.65
     induk
    0.64
    Activations Density 0.746%

    No Known Activations