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. 23
    Prev
    Next
    INDEX
    Explanations

    content with a mix of personal reflections and specific details

    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

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.14
    0.9%
    421
    +0.13
    0.8%
    1127
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    421
    +0.14
    0.02
    1127
    +0.13
    0.02
    2034
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.90
    ⓧ
    -0.95
    <?
    -0.83
    /**
    -0.78
    /***
    
    -0.67
    Сол
    -0.65
     Normdatei
    -0.62
     springfox
    -0.62
     bezeichneter
    -0.61
    Высота
    -0.60
    POSITIVE LOGITS
     '..
    0.92
     velours
    0.89
    ">...
    0.88
    )..
    0.87
    '..
    0.85
     véhic
    0.84
    ..
    0.83
     "..
    0.82
     maroc
    0.80
     impractica
    0.80
    Activations Density 0.079%

    No Known Activations