© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3342
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of control and power dynamics, particularly in contexts of education and authority

    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
    1385
    +0.10
    0.3%
    152
    +0.09
    0.3%
    492
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.10
    0.03
    492
    +0.09
    0.04
    256
    +0.09
    0.03
    Negative Logits
     purcha
    -0.86
     effe
    -0.84
     increa
    -0.78
     alre
    -0.77
     fortn
    -0.75
     fta
    -0.73
     fuf
    -0.73
     fto
    -0.72
     affor
    -0.72
     fath
    -0.69
    POSITIVE LOGITS
     control
    0.85
     controlling
    0.77
     Ressources
    0.76
     controls
    0.75
     Control
    0.73
     controlled
    0.71
    control
    0.70
     CONTROL
    0.67
     Controls
    0.67
    Controls
    0.66
    Activations Density 0.166%

    No Known Activations