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. 14537
    Prev
    Next
    INDEX
    Explanations

    references to names of geographical locations and academic institutions

    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
    +0.29
    1.4%
    2019
    +0.14
    0.7%
    382
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.29
    0.06
    924
    +0.14
    0.05
    1466
    +0.12
    0.04
    Negative Logits
    <bos>
    -2.53
    /**
    -1.14
    ⓧ
    -1.08
    
    
    -1.06
    <?
    -1.00
    /***
    
    -0.99
     quitted
    -0.85
     intersper
    -0.84
     overcrow
    -0.82
    <?
    
    -0.82
    POSITIVE LOGITS
     utensi
    0.56
     énon
    0.56
    "");
    0.56
    Sklici
    0.55
     Informações
    0.54
     miniatura
    0.54
     marea
    0.53
    "")
    0.52
    :].
    0.52
     ';
    
    0.50
    Activations Density 0.172%

    No Known Activations