© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6561
    Prev
    Next
    INDEX
    Explanations

    phrases related to methods and processes

    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
    573
    +0.08
    0.2%
    1987
    +0.07
    0.2%
    468
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    355
    +0.08
    0.04
    1249
    +0.07
    0.02
    1415
    +0.07
    0.02
    Negative Logits
     usus
    -0.68
     Hez
    -0.67
     XNUMX
    -0.66
     incess
    -0.66
     Libri
    -0.65
     Voi
    -0.65
     patrio
    -0.64
     Teks
    -0.62
    iented
    -0.61
     Keny
    -0.60
    POSITIVE LOGITS
    Gdzie
    0.66
    Przyp
    0.65
    Dzięki
    0.63
     pregă
    0.62
    Dazu
    0.62
    Dlaczego
    0.62
    mbggenerated
    0.61
    Zgod
    0.59
    Afin
    0.59
    Interess
    0.59
    Activations Density 0.235%

    No Known Activations