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. 618
    Prev
    Next
    INDEX
    Explanations

    phrases related to music lyrics or performance

    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
    1967
    +0.30
    1.4%
    50
    +0.22
    1.0%
    1839
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    577
    +0.30
    0.05
    1363
    +0.22
    0.05
    1978
    +0.15
    0.07
    Negative Logits
    <bos>
    -1.78
     abbra
    -0.90
    Autoritní
    -0.83
     anse
    -0.83
     ‹
    -0.81
     auton
    -0.81
     ویکی‌آمباردا
    -0.79
     glan
    -0.79
     solidar
    -0.77
     emble
    -0.77
    POSITIVE LOGITS
     ujedno
    0.64
     кіль
    0.62
     NavBar
    0.57
     UserData
    0.57
     blackish
    0.57
     potentialities
    0.56
    {*}
    0.56
     розта
    0.56
     такъ
    0.56
     BigNumber
    0.55
    Activations Density 0.945%

    No Known Activations