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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 902
    Prev
    Next
    INDEX
    Explanations

    words related to financial terms and events

    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
    597
    +0.07
    0.2%
    1950
    +0.07
    0.2%
    1820
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    356
    +0.07
    0.03
    733
    +0.07
    0.03
    597
    +0.07
    0.03
    Negative Logits
     seriously
    -0.64
     shook
    -0.59
     finally
    -0.59
     know
    -0.59
     actually
    -0.58
    起来
    -0.57
     certainly
    -0.57
     previously
    -0.56
     reflect
    -0.56
     served
    -0.56
    POSITIVE LOGITS
    outs
    2.34
     outs
    2.19
     Outs
    1.83
    Outs
    1.78
     sappi
    1.47
     outlander
    1.46
     hcm
    1.39
     stockholm
    1.38
     applau
    1.38
     Ottobre
    1.37
    Activations Density 0.192%

    No Known Activations