© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14485
    Prev
    Next
    INDEX
    Explanations

    phrases related to complex arguments or discussions

    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
    1577
    +0.51
    2.0%
    599
    +0.25
    1.0%
    1224
    +0.19
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    599
    +0.51
    0.20
    1577
    +0.25
    0.20
    184
    +0.19
    0.03
    Negative Logits
     Whence
    -0.75
     Shakspeare
    -0.75
     Abbé
    -0.68
     Rodrig
    -0.67
     McLaugh
    -0.66
     Incenti
    -0.65
     Augu
    -0.65
     Bartholo
    -0.64
     Mlle
    -0.64
     Thier
    -0.62
    POSITIVE LOGITS
     ویکی‌پدیا
    0.55
    ьаж
    0.54
     HttpNotFound
    0.54
     ویکی‌پدیای
    0.44
    SharedDtor
    0.44
    mercial
    0.42
    asics
    0.42
     [...]
    0.41
    itecture
    0.41
    adaptiveStyles
    0.41
    Activations Density 5.754%

    No Known Activations