© 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. 6002
    Prev
    Next
    INDEX
    Explanations

    terms related to significant events or features in a context of professional sports and politics

    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
    1013
    +0.09
    0.3%
    1634
    +0.09
    0.3%
    1042
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1867
    +0.09
    0.04
    342
    +0.09
    0.05
    1675
    +0.09
    0.06
    Negative Logits
     „,
    -1.03
     Intere
    -0.98
     depic
    -0.95
     bett
    -0.93
     fuf
    -0.93
     wien
    -0.92
     tew
    -0.91
     spont
    -0.90
     madonna
    -0.90
     Pamph
    -0.89
    POSITIVE LOGITS
     big
    0.74
    big
    0.72
    Big
    0.68
    大的
    0.67
     Big
    0.66
    Large
    0.65
     large
    0.65
     giant
    0.64
     Large
    0.63
    large
    0.62
    Activations Density 0.589%

    No Known Activations