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. 819
    Prev
    Next
    INDEX
    Explanations

    keywords related to home furnishings or products in a specific collection

    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
    678
    +0.13
    0.5%
    630
    +0.13
    0.5%
    1406
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.13
    0.09
    678
    +0.13
    0.07
    1056
    +0.13
    0.07
    Negative Logits
    IndentedString
    -0.87
    GEBURTSDATUM
    -0.84
     الرياضيه
    -0.82
    contentLoaded
    -0.80
     kasarigan
    -0.80
     disambiguazione
    -0.79
    Vidite
    -0.78
    躇
    -0.73
    <bos>
    -0.70
    Rujuakan
    -0.68
    POSITIVE LOGITS
     héro
    1.03
     catég
    0.95
     téléph
    0.92
     vété
    0.90
     merveilleux
    0.89
     rafra
    0.87
    emmel
    0.84
     cryst
    0.83
     tremp
    0.82
     alkoh
    0.81
    Activations Density 0.345%

    No Known Activations