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. 14751
    Prev
    Next
    INDEX
    Explanations

    descriptions of accommodations at a resort or hotel, focusing on amenities and facilities

    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
    +0.28
    1.1%
    1013
    +0.10
    0.4%
    1120
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.28
    0.04
    1446
    +0.10
    0.07
    1511
    +0.09
    0.02
    Negative Logits
    <bos>
    -1.93
    ⓧ
    -0.91
    
    
    -0.82
     disbur
    -0.77
    <?
    -0.76
     ratify
    -0.72
    /**
    -0.71
     endow
    -0.71
     intersper
    -0.70
     sympathize
    -0.69
    POSITIVE LOGITS
     délib
    0.98
     déliv
    0.97
     prét
    0.97
     écout
    0.96
     véhic
    0.96
     épu
    0.92
     considér
    0.89
     soulign
    0.86
     dépens
    0.86
     vété
    0.86
    Activations Density 0.866%

    No Known Activations