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. 14926
    Prev
    Next
    INDEX
    Explanations

    terms related to interference, such as "interference of waves" and "work interference."

    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
    1742
    +0.18
    1.0%
    1339
    +0.15
    0.9%
    161
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.18
    0.04
    1363
    +0.15
    0.04
    732
    +0.14
    0.03
    Negative Logits
    <bos>
    -0.96
    Conteúdo
    -0.65
    Boletín
    -0.64
    Edición
    -0.63
    Conclusión
    -0.63
    model
    -0.62
    Cual
    -0.61
    Argumento
    -0.61
    edu
    -0.61
    Vegeu
    -0.61
    POSITIVE LOGITS
     maneu
    1.31
     hentai
    1.22
     snoopy
    1.22
     milf
    1.22
     panama
    1.21
     yves
    1.19
     sandra
    1.19
     impra
    1.19
     unspeak
    1.19
     erad
    1.18
    Activations Density 0.894%

    No Known Activations