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. 14911
    Prev
    Next
    INDEX
    Explanations

    phrases related to awareness or understanding

    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
    1077
    +0.09
    0.3%
    1904
    +0.08
    0.2%
    1731
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.09
    0.04
    1951
    +0.08
    0.04
    1983
    +0.08
    0.03
    Negative Logits
     zumal
    -0.65
     defaultstate
    -0.62
     worin
    -0.62
    存于互联网档案馆
    -0.58
     weshalb
    -0.57
    crí
    -0.54
    Geplaatst
    -0.54
    IVEREF
    -0.53
     firent
    -0.53
     worauf
    -0.53
    POSITIVE LOGITS
     poire
    0.66
     shenan
    0.65
     saumon
    0.60
     Knew
    0.58
     baka
    0.57
     persil
    0.57
     knew
    0.57
     chèvre
    0.56
    wouldn
    0.55
     scopri
    0.55
    Activations Density 0.453%

    No Known Activations