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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14814
    Prev
    Next
    INDEX
    Explanations

    mentions of poverty

    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
    101
    +0.18
    0.9%
    241
    +0.16
    0.8%
    1335
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1741
    +0.18
    -0.00
    1363
    +0.16
    0.03
    241
    +0.13
    0.03
    Negative Logits
     intersper
    -1.32
     quitted
    -1.05
     impelled
    -1.03
     assailed
    -0.99
     vainly
    -0.98
     gaily
    -0.98
     tolerably
    -0.97
     unspeak
    -0.96
     shewn
    -0.96
     forbear
    -0.94
    POSITIVE LOGITS
     Poverty
    1.01
     poverty
    0.99
    Poverty
    0.88
    poverty
    0.85
     chèvre
    0.84
     frambo
    0.83
     marte
    0.75
     frites
    0.73
     tila
    0.72
     tomat
    0.71
    Activations Density 0.527%

    No Known Activations