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. 875
    Prev
    Next
    INDEX
    Explanations

    phrases related to philosophy or musings about life

    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
    +0.24
    1.4%
    1053
    +0.12
    0.7%
    32
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1053
    +0.24
    0.12
    32
    +0.12
    0.11
    645
    +0.12
    0.10
    Negative Logits
    <bos>
    -3.33
     jsPsych
    -0.78
    ⓧ
    -0.78
    /**
    -0.62
    Descripció
    -0.58
     Numerade
    -0.58
    <tfoot>
    -0.58
    EndProject
    -0.58
    Geplaatst
    -0.57
    lateinit
    -0.57
    POSITIVE LOGITS
     swarovski
    1.31
     chrysler
    1.28
     eiffel
    1.23
     practition
    1.22
     lamborghini
    1.19
     sappi
    1.16
     viciss
    1.15
     tupperware
    1.15
     panasonic
    1.14
     mitsubishi
    1.12
    Activations Density 0.383%

    No Known Activations