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. 1525
    Prev
    Next
    INDEX
    Explanations

    references to physical actions or qualities related to 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
    690
    +0.08
    0.2%
    1385
    +0.08
    0.2%
    2045
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.08
    0.06
    509
    +0.08
    0.05
    1246
    +0.07
    0.04
    Negative Logits
     increa
    -1.67
     emphat
    -1.64
     effe
    -1.58
     encomp
    -1.57
     reluct
    -1.56
     alre
    -1.55
     fta
    -1.53
     suscep
    -1.51
     impra
    -1.51
     accla
    -1.51
    POSITIVE LOGITS
     until
    0.98
     throughout
    0.97
     while
    0.86
     despite
    0.84
     during
    0.84
    until
    0.82
     till
    0.80
    keep
    0.79
     maintained
    0.77
    maintained
    0.77
    Activations Density 0.344%

    No Known Activations