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. 14582
    Prev
    Next
    INDEX
    Explanations

    statistical data or information related to global issues and conferences

    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
    +0.19
    0.7%
    1499
    +0.12
    0.4%
    1018
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.19
    0.09
    455
    +0.12
    0.04
    344
    +0.06
    0.01
    Negative Logits
    <bos>
    -2.93
    <?
    
    -0.70
     betweenstory
    -0.70
    verifyException
    -0.69
    ⓧ
    -0.69
     jsPsych
    -0.67
    /***
    
    -0.65
     ModelRenderer
    -0.64
    IsContent
    -0.64
    runApp
    -0.64
    POSITIVE LOGITS
     affor
    1.31
     bandung
    1.24
     Juf
    1.23
     santiago
    1.22
     pican
    1.21
     maneu
    1.21
     unlaw
    1.20
     véhic
    1.20
     unwarran
    1.19
     toledo
    1.17
    Activations Density 0.700%

    No Known Activations