© 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. 7052
    Prev
    Next
    INDEX
    Explanations

    requests for feedback from users

    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
    896
    +0.15
    0.5%
    1677
    +0.13
    0.4%
    1981
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    896
    +0.15
    0.02
    1981
    +0.13
    0.02
    1677
    +0.12
    0.02
    Negative Logits
     shenan
    -0.99
     accla
    -0.95
     disgra
    -0.93
     indestru
    -0.91
     emphat
    -0.89
     excru
    -0.86
     Perci
    -0.86
     reluct
    -0.86
     Mlle
    -0.83
     impra
    -0.83
    POSITIVE LOGITS
     feedback
    1.45
    feedback
    1.38
     Feedback
    1.33
    Feedback
    1.28
     FEEDBACK
    1.10
    FEEDBACK
    1.08
     feedbacks
    1.00
    反馈
    0.91
    edback
    0.73
     comentarios
    0.58
    Activations Density 0.082%

    No Known Activations