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. 10102
    Prev
    Next
    INDEX
    Explanations

    economic or financial terms and concepts

    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
    382
    +0.15
    0.5%
    2034
    +0.15
    0.5%
    1042
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.15
    0.08
    1265
    +0.15
    0.07
    908
    +0.13
    0.04
    Negative Logits
     mef
    -1.91
     lele
    -1.81
     franz
    -1.80
     ohr
    -1.76
     meis
    -1.74
     „,
    -1.71
     sii
    -1.71
     gend
    -1.68
     ?...
    -1.67
     fta
    -1.65
    POSITIVE LOGITS
     but
    1.17
     because
    1.01
     though
    0.99
     especially
    0.96
     although
    0.96
     however
    0.96
     since
    0.94
    but
    0.90
     nhưng
    0.89
     as
    0.86
    Activations Density 0.319%

    No Known Activations