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. 525
    Prev
    Next
    INDEX
    Explanations

    questions and exclamations

    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
    +0.18
    0.6%
    814
    +0.09
    0.3%
    789
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1109
    +0.18
    0.03
    851
    +0.09
    0.03
    1295
    +0.09
    0.03
    Negative Logits
    <bos>
    -2.31
    <?
    
    -0.64
    /***
    
    -0.61
    Autoritní
    -0.57
    Enllaços
    -0.57
    AsUp
    -0.57
    modelBuilder
    -0.57
    ########.
    -0.54
    djangoproject
    -0.53
    osoba
    -0.52
    POSITIVE LOGITS
     maneu
    1.01
     signora
    0.97
     maroc
    0.89
     reluct
    0.88
     pylab
    0.87
     psycopg
    0.87
     disagre
    0.86
     disreg
    0.81
     impra
    0.81
     fortn
    0.80
    Activations Density 0.114%

    No Known Activations