© 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. 4271
    Prev
    Next
    INDEX
    Explanations

    instances of words related to ongoing or continuing actions

    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
    120
    +0.13
    0.4%
    1793
    +0.11
    0.4%
    699
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1793
    +0.13
    0.06
    120
    +0.11
    0.05
    699
    +0.10
    0.05
    Negative Logits
     karton
    -0.60
     zó
    -0.56
     elek
    -0.55
     kram
    -0.54
     logis
    -0.54
    Bibliograf
    -0.51
     utop
    -0.51
    érêt
    -0.49
    StoreMessageInfo
    -0.49
     balon
    -0.48
    POSITIVE LOGITS
     continue
    0.84
     continued
    0.79
     continuing
    0.78
     continues
    0.77
    continue
    0.75
     CONTIN
    0.71
    continues
    0.70
     Continues
    0.70
     Continue
    0.69
    CONTINUE
    0.67
    Activations Density 0.106%

    No Known Activations