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

    Neuronpedia

    APICircuit 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. 6908
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and discussions related to political campaigns and appointments

    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
    +0.16
    0.6%
    604
    +0.09
    0.4%
    890
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    809
    +0.16
    0.08
    344
    +0.09
    0.02
    915
    +0.08
    0.07
    Negative Logits
    <bos>
    -2.96
     intersper
    -1.25
    /***
    
    -1.10
     encomp
    -1.05
    ⓧ
    -1.01
     quitted
    -0.98
     overcrow
    -0.94
     hairc
    -0.94
    
    
    -0.92
     endow
    -0.92
    POSITIVE LOGITS
     cabina
    0.68
     Jerusal
    0.66
     Gnaden
    0.65
     Mú
    0.65
     ajustable
    0.63
    cuerdo
    0.62
     augusti
    0.62
     +%
    0.61
     Spani
    0.61
     corrom
    0.61
    Activations Density 1.093%

    No Known Activations