Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 5920
    Prev
    Next
    INDEX
    Explanations

    phrases related to workforce diversity and inclusion initiatives, such as affirmative action, minority- and women-owned businesses, racial and ethnic disparities, and the importance of representation for underrepresented populations

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.22
    0.9%
    198
    +0.10
    0.4%
    521
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.22
    0.07
    1252
    +0.10
    0.06
    549
    +0.09
    0.06
    Negative Logits
    <bos>
    -3.01
     jsPsych
    -0.86
    Referències
    -0.83
    Enllaços
    -0.78
    HasColumnType
    -0.72
    Descripció
    -0.71
    tagHelperRunner
    -0.70
     gynhyrchwyd
    -0.70
    TagMode
    -0.67
     butterknife
    -0.67
    POSITIVE LOGITS
     Juf
    1.93
     increa
    1.93
     maneu
    1.90
     Augu
    1.89
     affor
    1.88
     Intere
    1.83
     inev
    1.82
     guarante
    1.80
     emphat
    1.78
     stockholm
    1.75
    Activations Density 0.498%

    No Known Activations