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. 5512
    Prev
    Next
    INDEX
    Explanations

    phrases related to seeking advice or recommendations

    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
    +0.20
    0.9%
    1839
    +0.10
    0.5%
    1339
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    629
    +0.20
    0.04
    1758
    +0.10
    0.04
    1491
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.56
    /***
    
    -0.88
    
    
    -0.75
     endow
    -0.71
     rehabilitate
    -0.68
     amass
    -0.67
     disbur
    -0.67
     neutralize
    -0.67
    //---
    -0.66
    <?
    -0.65
    POSITIVE LOGITS
     jawa
    1.04
     bandung
    1.04
     tramont
    0.97
     maroc
    0.92
     nuoc
    0.91
     sés
    0.91
     cæ
    0.90
     lele
    0.90
    ydın
    0.89
    lijah
    0.88
    Activations Density 0.166%

    No Known Activations