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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15324
    Prev
    Next
    INDEX
    Explanations

    file format extensions

    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
    1.1%
    966
    +0.12
    0.7%
    1404
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    966
    +0.18
    0.03
    1404
    +0.12
    0.03
    562
    +0.11
    0.03
    Negative Logits
    <bos>
    -3.04
    
    
    -1.12
    ⓧ
    -1.08
    /**
    -1.02
    <?
    -0.82
    /*
    -0.72
     springfox
    -0.67
    Життєпис
    -0.62
     gratify
    -0.60
     Normdatei
    -0.59
    POSITIVE LOGITS
     .
    0.97
     corrom
    0.88
     Minang
    0.84
     Hitam
    0.83
     Muhamma
    0.82
     bandung
    0.80
    ffiche
    0.80
     seksi
    0.80
     ados
    0.80
     Resmi
    0.78
    Activations Density 0.059%

    No Known Activations