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. 13327
    Prev
    Next
    INDEX
    Explanations

    phrases related to advocacy and urging action

    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
    1516
    +0.10
    0.4%
    1053
    +0.10
    0.3%
    67
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    973
    +0.10
    0.05
    67
    +0.10
    0.04
    1516
    +0.09
    0.04
    Negative Logits
     préfère
    -0.70
     Agustín
    -0.68
     Asunción
    -0.68
     Lázaro
    -0.67
     Áng
    -0.65
     Aguas
    -0.63
     Almería
    -0.61
     Ávila
    -0.60
     Mejía
    -0.59
     serai
    -0.59
    POSITIVE LOGITS
     NEED
    0.84
     need
    0.83
    need
    0.81
    Need
    0.78
     Need
    0.78
    needs
    0.74
     needs
    0.71
     Needs
    0.71
    NEED
    0.70
     NEEDS
    0.69
    Activations Density 0.102%

    No Known Activations