© 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. 2294
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical figures commonly related to aviation such as the Wright brothers

    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
    1103
    +0.07
    0.2%
    1961
    +0.07
    0.2%
    890
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    952
    +0.07
    0.02
    890
    +0.07
    0.02
    1329
    +0.07
    0.02
    Negative Logits
     draw
    -0.72
     бо
    -0.69
     поло
    -0.65
     die
    -0.64
     meet
    -0.63
     come
    -0.62
    フィ
    -0.62
     ask
    -0.62
     came
    -0.62
    а
    -0.62
    POSITIVE LOGITS
     Wright
    2.52
     wright
    2.46
    Wright
    2.29
     WRIGHT
    2.08
     madonna
    1.70
     stockholm
    1.69
     accla
    1.66
     jacques
    1.62
     franz
    1.56
     mef
    1.56
    Activations Density 0.111%

    No Known Activations