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. 8865
    Prev
    Next
    INDEX
    Explanations

    names or terms related to specific individuals named "Kaus"

    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
    1276
    +0.23
    1.2%
    1472
    +0.21
    1.1%
    1187
    +0.17
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1276
    +0.23
    0.04
    1472
    +0.21
    0.03
    1343
    +0.17
    0.04
    Negative Logits
    <bos>
    -1.08
     שוליים
    -0.73
    queline
    -0.66
    redited
    -0.63
     Chwiliwch
    -0.61
    verwijspagina
    -0.60
    ciple
    -0.57
    ždý
    -0.57
    Referències
    -0.56
    rungsseite
    -0.55
    POSITIVE LOGITS
     Ka
    1.54
    Ka
    1.44
     ka
    1.13
     pylab
    1.02
     excru
    0.99
     KA
    0.97
     unspeak
    0.93
     récomp
    0.92
     pymysql
    0.89
     gaily
    0.87
    Activations Density 0.372%

    No Known Activations