Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 0
    Prev
    Next
    INDEX
    Explanations

    references to events or gatherings happening in a specific location

    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
    •Test List With Features

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    390
    +0.12
    0.6%
    313
    +0.11
    0.5%
    1527
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.12
    0.03
    1590
    +0.11
    0.03
    405
    +0.10
    0.02
    Negative Logits
    <bos>
    -1.82
    Vegeu
    -0.91
    ždý
    -0.62
    Externé
    -0.61
    Conteúdo
    -0.60
    Vanjske
    -0.60
    /***
    
    -0.59
     בְּ
    -0.58
    película
    -0.58
    Carreira
    -0.58
    POSITIVE LOGITS
     Reception
    1.33
     reception
    1.32
    reception
    1.25
     receptions
    1.22
    Reception
    1.17
     RECE
    1.16
     receptionist
    1.04
     tucson
    1.04
     jaya
    0.99
     receivers
    0.99
    Activations Density 0.235%

    No Known Activations