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. 14570
    Prev
    Next
    INDEX
    Explanations

    alphabet letters in strings that are in reverse order

    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
    2011
    +0.17
    0.9%
    1178
    +0.16
    0.9%
    1637
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1178
    +0.17
    0.03
    1047
    +0.16
    0.03
    227
    +0.16
    0.04
    Negative Logits
    <bos>
    -1.75
    oznam
    -0.70
    SizeMode
    -0.57
    /*!
    
    -0.57
    /**
    -0.54
    ⓧ
    -0.54
     насељу
    -0.54
    <!--
    
    -0.53
    ربای
    -0.53
    Cursors
    -0.52
    POSITIVE LOGITS
     Z
    1.09
    Z
    0.94
     actionTypes
    0.82
     Wtf
    0.81
     prêtre
    0.80
     Normalmente
    0.77
     Hauteur
    0.76
     Lmao
    0.75
     🤣🤣
    0.75
     TMPro
    0.75
    Activations Density 0.350%

    No Known Activations