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. 8872
    Prev
    Next
    INDEX
    Explanations

    mentions of the TV show "Supernatural" or related terms like "Supernatural episode" or "Bobby's soul quest."

    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
    +0.17
    1.0%
    1407
    +0.10
    0.6%
    755
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    755
    +0.17
    0.04
    164
    +0.10
    0.03
    636
    +0.09
    0.03
    Negative Logits
    <bos>
    -3.50
    ⓧ
    -0.88
    HasIndex
    -0.80
    /**
    -0.79
    /*++
    -0.76
        
    -0.76
    #![
    -0.71
     manage
    -0.70
    /**
    -0.70
       
    -0.70
    POSITIVE LOGITS
     Juf
    2.04
     Minang
    1.97
     Keny
    1.83
     sovere
    1.82
     Confu
    1.82
     philanth
    1.78
     aen
    1.75
     impractica
    1.75
     accla
    1.75
     unlaw
    1.75
    Activations Density 0.081%

    No Known Activations