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. 15225
    Prev
    Next
    INDEX
    Explanations

    word(s) related to targets or objectives

    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
    1271
    +0.16
    0.6%
    420
    +0.12
    0.5%
    1323
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1271
    +0.16
    0.04
    420
    +0.12
    0.04
    1810
    +0.12
    0.03
    Negative Logits
     Sax
    -0.49
     leggera
    -0.46
     Lega
    -0.45
     Kyrgyz
    -0.43
     Leich
    -0.42
      
    -0.41
    nrows
    -0.41
     Spi
    -0.41
     Nea
    -0.40
     Umb
    -0.40
    POSITIVE LOGITS
     targets
    1.27
     Targets
    1.25
     target
    1.22
    target
    1.16
     Target
    1.16
    targets
    1.15
    Target
    1.12
     TARGET
    1.11
     targeting
    1.07
    TARGET
    1.05
    Activations Density 0.092%

    No Known Activations