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. 15150
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Patriot" or related terms

    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
    900
    +0.14
    0.7%
    1921
    +0.14
    0.7%
    325
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.14
    0.04
    1741
    +0.14
    -0.00
    1097
    +0.13
    0.05
    Negative Logits
     despotism
    -0.92
    <bos>
    -0.74
     zipfile
    -0.73
     heapq
    -0.72
     smtplib
    -0.70
     pymysql
    -0.69
    ഊ
    -0.65
    <?
    -0.65
     pamph
    -0.65
    ellemző
    -0.65
    POSITIVE LOGITS
     pira
    0.79
     Patriots
    0.78
     ADT
    0.75
     Somal
    0.73
     nutr
    0.73
     Patriot
    0.73
     obser
    0.73
     anton
    0.73
     ordina
    0.72
    Patriot
    0.72
    Activations Density 0.675%

    No Known Activations