© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2323
    Prev
    Next
    INDEX
    Explanations

    phrases that include variations of the word "upon"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    798
    +0.09
    0.3%
    644
    +0.06
    0.2%
    594
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.09
    0.06
    798
    +0.06
    0.05
    1499
    +0.06
    0.07
    Negative Logits
    大
    -0.90
    ,
    -0.87
    .
    -0.87
     could
    -0.87
     im
    -0.87
    ・
    -0.86
    <eos>
    -0.86
    加
    -0.84
    :
    -0.84
     can
    -0.84
    POSITIVE LOGITS
     maneu
    2.88
     indestru
    2.78
     impra
    2.70
     hentai
    2.69
     emphat
    2.69
     disagre
    2.67
     excru
    2.66
     Juf
    2.65
     jorge
    2.65
     milf
    2.65
    Activations Density 1.105%

    No Known Activations