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. 15207
    Prev
    Next
    INDEX
    Explanations

    websites or domains

    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
    +0.18
    0.7%
    1224
    +0.07
    0.3%
    766
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    924
    +0.18
    0.12
    1003
    +0.07
    0.09
    304
    +0.07
    -0.01
    Negative Logits
    <bos>
    -2.40
    /***
    
    -0.94
    ⓧ
    -0.89
    /**
    -0.78
    
    
    -0.73
    <?
    
    -0.71
    LayoutStyle
    -0.71
    AddTagHelper
    -0.70
    //});
    -0.69
    HasIndex
    -0.69
    POSITIVE LOGITS
     maneu
    1.49
     Varan
    1.34
     fortn
    1.29
     impra
    1.28
     Intere
    1.25
     attemp
    1.24
     affor
    1.24
     resear
    1.23
     Juf
    1.22
     Khart
    1.22
    Activations Density 0.881%

    No Known Activations