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. 1314
    Prev
    Next
    INDEX
    Explanations

    references to specific activities or actions involving objects

    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
    50
    +0.25
    0.9%
    1385
    +0.23
    0.8%
    1741
    +0.19
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.25
    0.07
    946
    +0.23
    0.07
    16
    +0.19
    0.07
    Negative Logits
     kontinu
    -1.05
     kompati
    -0.98
     Mémoires
    -0.96
     chande
    -0.95
     tremb
    -0.95
     silikon
    -0.94
     protokol
    -0.93
     plis
    -0.92
     akut
    -0.90
     pecuni
    -0.89
    POSITIVE LOGITS
     entire
    0.71
     rest
    0.63
    Wichtig
    0.63
    Inne
    0.63
    Pozdrawiam
    0.60
     whole
    0.60
     same
    0.59
    Glej
    0.58
    Sklici
    0.58
     latter
    0.57
    Activations Density 0.482%

    No Known Activations