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. 15059
    Prev
    Next
    INDEX
    Explanations

    mentions of the city "Venice" in different contexts

    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
    871
    +0.21
    1.1%
    101
    +0.17
    0.9%
    313
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1741
    +0.21
    0.00
    478
    +0.17
    0.03
    227
    +0.16
    0.07
    Negative Logits
    <bos>
    -0.99
    browserify
    -0.58
    WriteTagHelper
    -0.56
    Sqft
    -0.53
    pulumi
    -0.53
    array
    -0.52
    ㎝
    -0.52
    addCriterion
    -0.51
    olol
    -0.51
    webdriver
    -0.50
    POSITIVE LOGITS
     jorge
    1.49
     sergio
    1.33
     javier
    1.28
     lorenzo
    1.28
     reluct
    1.23
     ricardo
    1.20
     milf
    1.19
     alberto
    1.17
     fernando
    1.17
     unlaw
    1.16
    Activations Density 0.700%

    No Known Activations