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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 12-RES-JB
    6. 156
    Prev
    Next
    INDEX
    Explanations

    instances of conjunctions, particularly "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.38
    1.3%
    2019
    +0.11
    0.4%
    1265
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.38
    0.05
    1806
    +0.11
    0.04
    1415
    +0.10
    0.05
    Negative Logits
     intersper
    -1.05
     felicity
    -0.90
     encomp
    -0.87
     liberality
    -0.87
     Thos
    -0.86
     quitted
    -0.82
     Pamph
    -0.82
     gaily
    -0.81
     Shakspeare
    -0.79
     Augu
    -0.76
    POSITIVE LOGITS
    GYPT
    0.74
     Muito
    0.73
     Talvez
    0.72
     Adicion
    0.72
    sizePolicy
    0.71
     Estou
    0.69
     Hitam
    0.68
    visející
    0.67
     confronti
    0.67
     Saludos
    0.65
    Activations Density 0.277%

    No Known Activations