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. 15249
    Prev
    Next
    INDEX
    Explanations

    words related to physical or emotional pain and injury

    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
    0.9%
    1034
    +0.10
    0.6%
    663
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.17
    0.02
    468
    +0.10
    0.02
    147
    +0.09
    0.01
    Negative Logits
    <bos>
    -3.37
    ⓧ
    -0.91
     насеља
    -0.80
    
    
    -0.74
    public
    -0.73
    Kontrola
    -0.71
    /**
    -0.69
    /*
    -0.69
    HasColumnType
    -0.68
    Ба
    -0.68
    POSITIVE LOGITS
     stockholm
    1.74
     wien
    1.65
     Czechos
    1.61
     dises
    1.61
     frankfurt
    1.61
     Minang
    1.58
     eiffel
    1.58
     riva
    1.58
     riviera
    1.56
     Juf
    1.56
    Activations Density 0.090%

    No Known Activations