© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 14850
    Prev
    Next
    INDEX
    Explanations

    financial figures and numerical values

    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
    1042
    +0.08
    0.2%
    581
    +0.08
    0.2%
    861
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    861
    +0.08
    0.06
    1834
    +0.08
    0.04
    799
    +0.07
    0.04
    Negative Logits
     tranf
    -0.97
     fup
    -0.94
     occafion
    -0.87
     ftu
    -0.83
     feen
    -0.82
     lefs
    -0.82
     perfon
    -0.82
     prefent
    -0.81
     ftre
    -0.80
     fatis
    -0.79
    POSITIVE LOGITS
     sales
    0.52
     blockbuster
    0.51
     weekend
    0.50
    venues
    0.49
     debuted
    0.48
     debut
    0.48
     bookings
    0.47
     revenues
    0.46
     cinemas
    0.46
     rebound
    0.46
    Activations Density 0.377%

    No Known Activations