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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5598
    Prev
    Next
    INDEX
    Explanations

    information related to fundraising events for cancer research and breast cancer awareness

    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
    +0.24
    0.9%
    855
    +0.06
    0.2%
    1589
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.24
    0.05
    1217
    +0.06
    0.06
    855
    +0.06
    0.05
    Negative Logits
    <bos>
    -2.21
     springfox
    -0.61
    <?
    
    -0.53
     pneumo
    -0.52
     germinate
    -0.51
    /*!
    
    -0.50
     enshr
    -0.50
    ⓧ
    -0.50
     consolidate
    -0.49
     setObject
    -0.49
    POSITIVE LOGITS
     saar
    1.32
     lele
    1.22
     Jambi
    1.21
     Minang
    1.18
     Muhamma
    1.15
     seksi
    1.14
     Palembang
    1.11
     hcm
    1.11
     Pekan
    1.11
     Keny
    1.10
    Activations Density 0.745%

    No Known Activations