Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 534
    Prev
    Next
    INDEX
    Explanations

    instances where the word "back" is repeated in proximity

    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%
    674
    +0.12
    0.4%
    404
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.14
    0.06
    1961
    +0.12
    0.06
    101
    +0.11
    0.05
    Negative Logits
     abnorm
    -0.83
     zyn
    -0.77
     albic
    -0.74
     salomon
    -0.72
     fei
    -0.70
     drey
    -0.70
     zoll
    -0.69
     meis
    -0.69
     dora
    -0.69
     emphat
    -0.69
    POSITIVE LOGITS
     back
    1.23
    back
    1.15
     Back
    1.15
     BACK
    1.14
    Back
    1.08
    BACK
    1.05
    backs
    0.92
     backs
    0.88
    バック
    0.77
     zurück
    0.74
    Activations Density 0.118%

    No Known Activations