© 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. 3532
    Prev
    Next
    INDEX
    Explanations

    specific instances of the name "Greg"

    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
    241
    +0.16
    0.7%
    122
    +0.15
    0.6%
    1573
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1573
    +0.16
    0.02
    241
    +0.15
    0.02
    122
    +0.15
    0.02
    Negative Logits
     Carlin
    -0.54
     machine
    -0.50
     Salter
    -0.49
    エル
    -0.47
     Shaffer
    -0.47
     ceasing
    -0.47
     Pierson
    -0.46
     Dunlap
    -0.46
     Фа
    -0.46
     surface
    -0.45
    POSITIVE LOGITS
     Greg
    1.38
    Greg
    1.29
     GREG
    1.26
     Traité
    1.10
    GREG
    1.09
     greg
    1.07
    greg
    1.01
     Sén
    1.01
    Gregory
    0.98
     Gregory
    0.97
    Activations Density 0.076%

    No Known Activations