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. 1310
    Prev
    Next
    INDEX
    Explanations

    related to historical, political or philosophical discussions, especially regarding debate, democracy, and decision-making

    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
    849
    +0.10
    0.3%
    437
    +0.09
    0.3%
    900
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    849
    +0.10
    0.03
    1262
    +0.09
    0.02
    437
    +0.09
    0.02
    Negative Logits
     Juf
    -0.66
     Bagdad
    -0.62
     Fulda
    -0.62
     Hauptmann
    -0.58
     Amiens
    -0.58
     Neum
    -0.57
     Khart
    -0.56
     Glou
    -0.55
     Breslau
    -0.55
     Chartres
    -0.55
    POSITIVE LOGITS
    ">/
    0.84
    ">.
    0.82
    ">...
    0.77
    ">“
    0.74
    ">:
    0.69
     intitulée
    0.67
     bonté
    0.66
    ">+
    0.65
     contribue
    0.64
     prouve
    0.63
    Activations Density 0.187%

    No Known Activations