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. 15074
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Justin" followed by a surname, such as "Justin Bieber" or "Justin Maxwell"

    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
    1334
    +0.17
    0.9%
    1472
    +0.15
    0.8%
    313
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.17
    0.03
    1575
    +0.15
    0.03
    1334
    +0.14
    0.03
    Negative Logits
    <bos>
    -1.13
    ⓧ
    -0.69
    více
    -0.57
    Zdroje
    -0.57
    
    
    -0.57
     jakarta
    -0.57
    Tác
    -0.57
    outSlope
    -0.55
    WithMany
    -0.54
     springfox
    -0.52
    POSITIVE LOGITS
     Justin
    1.65
    Justin
    1.61
     justin
    1.46
    justin
    1.30
     Bie
    0.89
    Bie
    0.87
     bieber
    0.87
     Justine
    0.86
     Justi
    0.85
     Bieber
    0.81
    Activations Density 0.368%

    No Known Activations