© 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. 12743
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the back or back-related 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
    1961
    +0.14
    0.5%
    866
    +0.13
    0.5%
    101
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    101
    +0.14
    0.05
    866
    +0.13
    0.04
    1961
    +0.13
    0.05
    Negative Logits
     impra
    -0.59
     Alab
    -0.58
     incu
    -0.57
     Dimin
    -0.57
     unce
    -0.56
     Glou
    -0.55
     Lumia
    -0.54
     maneu
    -0.53
     cloche
    -0.53
     Nautilus
    -0.52
    POSITIVE LOGITS
    back
    1.26
    Back
    1.19
    BACK
    1.18
     Back
    1.17
     BACK
    1.15
     back
    1.15
    backs
    1.12
     backs
    1.03
    backed
    0.92
    バック
    0.87
    Activations Density 0.104%

    No Known Activations