© 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. 1610
    Prev
    Next
    INDEX
    Explanations

    references to secularism and religious matters

    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
    1896
    +0.13
    0.4%
    1140
    +0.11
    0.3%
    1691
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1896
    +0.13
    0.02
    1343
    +0.11
    0.03
    1120
    +0.08
    0.03
    Negative Logits
    <bos>
    -0.82
     overcrow
    -0.54
     timelapse
    -0.51
     reccom
    -0.51
     relinquished
    -0.51
     cull
    -0.49
     retards
    -0.49
     adapts
    -0.48
     rewatch
    -0.48
     amass
    -0.48
    POSITIVE LOGITS
     secular
    1.37
     spouse
    1.28
     spouses
    1.18
     Bekasi
    1.11
    spouse
    1.09
     Spouse
    1.07
    usky
    1.01
     Secular
    1.01
    Spouse
    0.97
     Minang
    0.87
    Activations Density 0.257%

    No Known Activations