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. 804
    Prev
    Next
    INDEX
    Explanations

    salutations in the form "Mr. Lastname"

    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
    +0.19
    1.1%
    1516
    +0.11
    0.6%
    1994
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1516
    +0.19
    0.05
    1994
    +0.11
    0.04
    1110
    +0.10
    0.04
    Negative Logits
    <bos>
    -3.06
    ⓧ
    -0.88
     disbur
    -0.88
     endow
    -0.81
    
    
    -0.80
     defray
    -0.78
     harmonize
    -0.78
    /**
    -0.76
     inaugurate
    -0.75
     springfox
    -0.74
    POSITIVE LOGITS
     Mr
    1.21
    Mr
    1.16
     mr
    0.98
     véhic
    0.96
     Outils
    0.91
     quoique
    0.89
     délib
    0.88
     considér
    0.86
     Présentation
    0.85
     rafra
    0.84
    Activations Density 0.084%

    No Known Activations