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. 15161
    Prev
    Next
    INDEX
    Explanations

    phrases related to sanding

    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
    32
    +0.15
    0.9%
    1222
    +0.15
    0.9%
    1323
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1222
    +0.15
    0.03
    32
    +0.15
    0.03
    68
    +0.13
    0.03
    Negative Logits
    <bos>
    -2.50
    ⓧ
    -0.66
    public
    -0.57
    echo
    -0.57
     inaugurate
    -0.55
    /**
    -0.55
    /*
    -0.55
    export
    -0.54
    queryInterface
    -0.54
    <?
    
    -0.54
    POSITIVE LOGITS
     Sand
    1.52
    Sand
    1.46
     SAND
    1.43
     sand
    1.43
    sand
    1.31
    SAND
    1.29
     pymysql
    1.21
     sands
    1.16
     Sandwiches
    1.10
     Sandman
    1.05
    Activations Density 0.131%

    No Known Activations