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

    Neuronpedia

    Jacobian LensNEW
    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. 5508
    Prev
    Next
    INDEX
    Explanations

    phrases related to asking for or providing comments or explanations

    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
    1150
    +0.15
    0.4%
    468
    +0.11
    0.3%
    1618
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1309
    +0.15
    0.03
    1150
    +0.11
    0.02
    968
    +0.10
    0.03
    Negative Logits
     bordeaux
    -1.08
     ecru
    -1.06
     fluo
    -1.02
     tricot
    -1.02
     broderie
    -0.98
     swarovski
    -0.98
     !...
    -0.97
     madonna
    -0.96
     nutella
    -0.95
     coq
    -0.94
    POSITIVE LOGITS
     whether
    0.57
     questions
    0.56
     matters
    0.56
     specific
    0.56
    ագրություններ
    0.55
     question
    0.55
     any
    0.55
     comment
    0.55
     rumors
    0.55
     allegations
    0.55
    Activations Density 0.143%

    No Known Activations