© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 1606
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "client"

    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
    +0.21
    1.3%
    168
    +0.12
    0.7%
    687
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.21
    0.04
    2004
    +0.12
    0.03
    1392
    +0.12
    0.03
    Negative Logits
    <bos>
    -2.96
     intersper
    -1.49
     endow
    -1.14
     quitted
    -1.09
     disbur
    -1.09
     encomp
    -1.07
     enshr
    -1.05
     trod
    -1.01
     chanced
    -1.00
     gratify
    -1.00
    POSITIVE LOGITS
     client
    1.31
     Client
    1.25
     clients
    1.24
    client
    1.19
     Clients
    1.18
    Clients
    1.17
    Client
    1.16
     CLIENT
    1.09
    clients
    1.06
    CLIENT
    1.06
    Activations Density 0.084%

    No Known Activations