© 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. 4224
    Prev
    Next
    INDEX
    Explanations

    quoted speech followed by the word "say"

    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
    228
    +0.16
    0.6%
    920
    +0.14
    0.5%
    313
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    228
    +0.16
    0.07
    521
    +0.14
    0.06
    878
    +0.14
    0.06
    Negative Logits
     guma
    -0.63
    Kích
    -0.59
    arroll
    -0.58
    Ngoài
    -0.58
    /*
    -0.57
     nonatomic
    -0.56
    owohl
    -0.56
    Unione
    -0.56
    Nguồn
    -0.55
     iyong
    -0.54
    POSITIVE LOGITS
     shenan
    1.26
     unspeak
    1.24
     gaily
    1.19
     apprehen
    1.15
     reluct
    1.14
     pooh
    1.12
     reconno
    1.08
     hairc
    1.08
     indescri
    1.07
     milf
    1.06
    Activations Density 0.195%

    No Known Activations